---
title: "Speech Translation and the End-to-End Promise: Taking Stock of Where We Are (2020)"
description: "They propose a shared vocabulary for inference strategies and application requirements. 97 references, cited by 60 papers here."
authors: ["Matthias Sperber", "Matthias Paulik"]
year: 2020
venue: "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"
source: "https://aclanthology.org/2020.acl-main.661/"
doi: "10.18653/v1/2020.acl-main.661"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/sperber-2020-speech-translation-end-end-promise/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sperber-2020-speech-translation-end-end-promise/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2020](https://md.research.elamur.ai/free/en/papers/2020/page/4/) / Speech Translation and the End-to-End Promise: Taking Stock of Where We Are

# Speech Translation and the End-to-End Promise: Taking Stock of Where We Are

**Authors:** Matthias Sperber and [Matthias Paulik](https://md.research.elamur.ai/free/en/authors/matthias-paulik/) · **Year:** 2020 · **Venue:** [Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2020](https://md.research.elamur.ai/free/en/venues/acl/2020/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2020.acl-main.661/) · [PDF](https://aclanthology.org/2020.acl-main.661.pdf) · [DOI 10.18653/v1/2020.acl-main.661](https://doi.org/10.18653/v1/2020.acl-main.661) · [OpenAlex](https://openalex.org/W3017258074)

**Citations:** 90 citations (OpenAlex, 2026-10-14) · [60](https://md.research.elamur.ai/free/en/papers/sperber-2020-speech-translation-end-end-promise/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
This ACL 2020 position paper by Sperber and Paulik asks why end-to-end speech translation (ST) models have had only mixed success against traditional cascades of ASR and MT. It contains no new experiments, dataset or model. Instead, the authors trace about thirty years of ST research:

- early loosely coupled cascades,
- tighter integration through n-best lists, lattices, FST composition and robustness training,
- the arrival of dedicated ST corpora,
- recent end-to-end models.

Comparing the two extremes, the 1-best cascade and the vanilla direct encoder-decoder, they identify four core problems: erroneous early decisions, mismatched source-language modeling, loss of speech information such as prosody, and data efficiency.

Their key observation is that end-to-end systems often bring cascade-like weaknesses back in when they use pre-training or multi-task learning to cope with scarce data. They propose a shared vocabulary for inference strategies and application requirements. This frames ST as a broad space of intermediate designs rather than a choice between cascaded and end-to-end. The framework is meant to support fairer comparisons and to point out open research directions.

## Key points
- **Six inference strategies** are named: committed cascade (CC), marginalizing cascade (MC), direct (Di), committed triangle (CT), marginalizing triangle (MT) and joint (Jt).
- **Empirical motivation:** Pham et al.'s system, which won the IWSLT 2019 shared ST task, was essentially a plain cascade built on modern ASR and MT components.
- **Data scarcity:** public end-to-end ST corpora are still small and cover few languages. Separate ASR and MT training data therefore remains unavoidable in practice.
- **Application requirements** are grouped by:
  - transcript role: mandatory, auxiliary, or transcript-free (e.g., unwritten endangered languages),
  - translation method: faithful vs. communicative (e.g., disfluency removal),
  - output medium: text vs. speech.
- **Suggested next steps:**
  - extend classic cascades rather than replace them, for example with end-to-end fine-tuning, direct-model rescoring or added triangle connections;
  - run user studies, since automatic metrics alone are not enough.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Apple](https://md.research.elamur.ai/free/en/companies/apple/) — Company, Cupertino, United States · 10 works · 1,972 citations
- [Apple (Israel)](https://md.research.elamur.ai/free/en/companies/apple-israel/) — Company, Herzliya, Israel · 4 works · 941 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 213 works

🧭 Topics (1): [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · 233 works

## Cite

Cite as: Matthias Sperber and Matthias Paulik. 2020. Speech Translation and the End-to-End Promise: Taking Stock of Where We Are. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{sperber2020speech,
  title = {{Speech Translation and the End-to-End Promise: Taking Stock of Where We Are}},
  author = {Matthias Sperber and Matthias Paulik},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.acl-main.661},
  url = {https://doi.org/10.18653/v1/2020.acl-main.661}
}
```

- [← previous INFOTABS: Inference on Tables as Semi-structured Data](https://md.research.elamur.ai/free/en/papers/gupta-2020-infotabs-inference-tables-as-semi/)
- [next → Statistical Power and Translationese in Machine Translation Evaluation](https://md.research.elamur.ai/free/en/papers/graham-2020-statistical-power-translationese-machine-translation/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/en/papers/2020/page/4/)

## References

97 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. P. D. Aguero, Jordi Adell, and Antonio Bonafonte. 2006. Prosody Generation for Speech-to-Speech Translation. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France. [find](https://scholar.google.com/scholar?q=P%2E+D%2E+Aguero%2C+Jordi+Adell%2C+and+Antonio+Bonafonte%2E+2006%2E+Prosody+Generation+for+Speech%2Dto%2DSpeech+Translation%2E+In+International+Conference+on+Acoustics%2C+Speech%2C+and+Signal+Processing+%28ICASSP%29%2C+Toulouse%2C)
2. Language Technology (SLT), pages 153–158, Miami, USA. [find](https://scholar.google.com/scholar?q=Language+Technology+%28SLT%29%2C+pages+153%E2%80%93158%2C+Miami%2C+USA%2E)
3. Necip Fazil Ayan, Arindam Mandal, Michael Frandsen, Jing Zheng, Peter Blasco, Andreas Kathol, Frederic Bechet, Benoit Favre, Alex Marin, Tom Kwiatkowski, Mari Ostendorf, Luke Zettlemoyer, Philipp Salletmayr, Julia Hirschberg, and Svetlana Stoyanchev. 2013. ’Can you give me another word for hyperbari… [find](https://scholar.google.com/scholar?q=Necip+Fazil+Ayan%2C+Arindam+Mandal%2C+Michael+Frandsen%2C+Jing+Zheng%2C+Peter+Blasco%2C+Andreas+Kathol%2C+Frederic+Bechet%2C+Benoit+Favre%2C+Alex+Marin%2C+Tom+Kwiatkowski%2C+Mari+Ostendorf%2C+Luke+Zettlemoyer%2C+Philipp+Sall)
4. Parnia Bahar, Albert Zeyer, Ralf Schlüter, and Hermann Ney. 2019. On Using SpecAugment for End-to-End Speech Translation. In International Workshop on Spoken Language Translation (IWSLT), Hongkong. [find](https://scholar.google.com/scholar?q=Parnia+Bahar%2C+Albert+Zeyer%2C+Ralf+Schlu%CC%88ter%2C+and+Hermann+Ney%2E+2019%2E+On+Using+SpecAugment+for+End%2Dto%2DEnd+Speech+Translation%2E+In+International+Workshop+on+Spoken+Language+Translation+%28IWSLT%29%2C+Hongkong%2E)
5. Srinivas Bangalore and Giuseppe Riccardi. 2001. A Finite-State Approach to Machine Translation. In North American Chapter of the Association for Computational Linguistics (NAACL), Pittsburgh, USA. [find](https://scholar.google.com/scholar?q=Srinivas+Bangalore+and+Giuseppe+Riccardi%2E+2001%2E+A+Finite%2DState+Approach+to+Machine+Translation%2E+In+North+American+Chapter+of+the+Association+for+Computational+Linguistics+%28NAACL%29%2C+Pittsburgh%2C+USA%2E)
6. Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, and Sharon Goldwater. 2018. Low-Resource Speech-to-Text Translation. In Annual Conference of the International Speech Communication Association (InterSpeech), Hyderabad, India. [find](https://scholar.google.com/scholar?q=Sameer+Bansal%2C+Herman+Kamper%2C+Karen+Livescu%2C+Adam+Lopez%2C+and+Sharon+Goldwater%2E+2018%2E+Low%2DResource+Speech%2Dto%2DText+Translation%2E+In+Annual+Conference+of+the+International+Speech+Communication+Association)
7. Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, and Sharon Goldwater. 2019. Pre-training on high-resource speech recognition improves low-resource speech-to-text translation. In North American Chapter of the Association for Computational Linguistics (NAACL), Minneapolis, USA. [our card](https://md.research.elamur.ai/free/en/papers/bansal-2019-pre-training-high-resource-speech/)
8. Sameer Bansal, Herman Kamper, Adam Lopez, and Sharon Goldwater. 2017. Towards speech-to-text translation without speech recognition. In European Chapter of the Association for Computational Linguistics (EACL). [find](https://scholar.google.com/scholar?q=Sameer+Bansal%2C+Herman+Kamper%2C+Adam+Lopez%2C+and+Sharon+Goldwater%2E+2017%2E+Towards+speech%2Dto%2Dtext+translation+without+speech+recognition%2E+In+European+Chapter+of+the+Association+for+Computational+Linguistic)
9. Daniel Beck, Trevor Cohn, and Gholamreza Haffari. 2019. Neural Speech Translation using Lattice Transformations and Graph Networks. In Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13), pages 26–31, Hongkong. [find](https://scholar.google.com/scholar?q=Daniel+Beck%2C+Trevor+Cohn%2C+and+Gholamreza+Haffari%2E+2019%2E+Neural+Speech+Translation+using+Lattice+Transformations+and+Graph+Networks%2E+In+Thirteenth+Workshop+on+Graph%2DBased+Methods+for+Natural+Language+P)
10. Benjamin Beilharz, Xin Sun, Sariya Karimova, and Stefan Riezler. 2020. LibriVoxDeEn: A Corpus for German-to-English Speech Translation and Speech Recognition. In Language Resources and Evaluation (LREC), Marseille, France. [find](https://scholar.google.com/scholar?q=Benjamin+Beilharz%2C+Xin+Sun%2C+Sariya+Karimova%2C+and+Stefan+Riezler%2E+2020%2E+LibriVoxDeEn%3A+A+Corpus+for+German%2Dto%2DEnglish+Speech+Translation+and+Speech+Recognition%2E+In+Language+Resources+and+Evaluation+%28LRE)
11. Antonios Anastasopoulos and David Chiang. 2018. Tied Multitask Learning for Neural Speech Translation. In North American Chapter of the Association for Computational Linguistics (NAACL), New Orleans, USA. [our card](https://md.research.elamur.ai/free/en/papers/anastasopoulos-2018-tied-multitask-learning-neural-speech/)
12. Yoshua Bengio, Nicholas Léonard, and Aaron Courville. 2013. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. arXiv:1308.3432. [find](https://scholar.google.com/scholar?q=Yoshua+Bengio%2C+Nicholas+Le%CC%81onard%2C+and+Aaron+Courville%2E+2013%2E+Estimating+or+Propagating+Gradients+Through+Stochastic+Neurons+for+Conditional+Computation%2E+arXiv%3A1308%2E3432%2E)
13. Gopala Krishna Anumanchipalli, Luis C. Oliveira, and Alan W. Black. 2012. Intent transfer in speech-to-speech machine translation. In Workshop on Spoken Alexandre Bérard, Laurent Besacier, Ali Can Kocabiyikoglu, and Olivier Pietquin. 2018. End-to-End Automatic Speech Translation of Audiobooks. [find](https://scholar.google.com/scholar?q=Gopala+Krishna+Anumanchipalli%2C+Luis+C%2E+Oliveira%2C+and+Alan+W%2E+Black%2E+2012%2E+Intent+transfer+in+speech%2Dto%2Dspeech+machine+translation%2E+In+Workshop+on+Spoken+Alexandre+Be%CC%81rard%2C+Laurent+Besacier%2C+Ali+Can+Ko)
14. Model Adaptation For Direct Speech Translation. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada. [find](https://scholar.google.com/scholar?q=Model+Adaptation+For+Direct+Speech+Translation%2E+In+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%28ICASSP%29%2C+Barcelona%2C+Spain%2E+In+International+Conference+on+Acoustics%2C+Speech+and+)
15. Alexandre Berard, Olivier Pietquin, Christophe Servan, and Laurent Besacier. 2016. Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation. In NIPS Workshop on End-to-end Learning for Speech and Audio Processing, Barcelona, Spain. [find](https://scholar.google.com/scholar?q=Alexandre+Berard%2C+Olivier+Pietquin%2C+Christophe+Servan%2C+and+Laurent+Besacier%2E+2016%2E+Listen+and+Translate%3A+A+Proof+of+Concept+for+End%2Dto%2DEnd+Speech%2Dto%2DText+Translation%2E+In+NIPS+Workshop+on+End%2Dto%2Dend+Le)
16. Paul R Dixon, Andrew Finch, H Chiori, and H Kashioka. 2011. Investigation on the Effects of ASR Tuning on Speech Translation Performance. In International Workshop on Spoken Language Translation (IWSLT), pages 167–174, San Francisco, USA. [find](https://scholar.google.com/scholar?q=Paul+R+Dixon%2C+Andrew+Finch%2C+H+Chiori%2C+and+H+Kashioka%2E+2011%2E+Investigation+on+the+Effects+of+ASR+Tuning+on+Speech+Translation+Performance%2E+In+International+Workshop+on+Spoken+Language+Translation+%28IWSL)
17. Nicola Bertoldi and Marcello Federico. 2005. A New Decoder for Spoken Language Translation Based on Confusion Networks. In Automatic Speech Recognition & Understanding (ASRU), pages 86–91, San Juan, Puerto Rico. [find](https://scholar.google.com/scholar?q=Nicola+Bertoldi+and+Marcello+Federico%2E+2005%2E+A+New+Decoder+for+Spoken+Language+Translation+Based+on+Confusion+Networks%2E+In+Automatic+Speech+Recognition+%26+Understanding+%28ASRU%29%2C+pages+86%E2%80%9391%2C+San+Juan%2C+P)
18. Quoc Truong Do, Tomoki Toda, Graham Neubig, Sakriani Sakti, and Satoshi Nakamura. 2017. Preserving Word-level Emphasis in Speech-to-speech Translation. IEEE Transactions on Audio, Speech and Language Processing, 25(3):544–556. [find](https://scholar.google.com/scholar?q=Quoc+Truong+Do%2C+Tomoki+Toda%2C+Graham+Neubig%2C+Sakriani+Sakti%2C+and+Satoshi+Nakamura%2E+2017%2E+Preserving+Word%2Dlevel+Emphasis+in+Speech%2Dto%2Dspeech+Translation%2E+IEEE+Transactions+on+Audio%2C+Speech+and+Language+)
19. Alan W. Black, Ralf D. Brown, Robert Frederking, Kevin Lenzo, John Moody, Alexander Rudnicky, Rita Singh, and Eric Steinbrecher. 2002. Rapid Development of Speech-to-Speech Translation Systems. In International Conference on Spoken Language Processing (ICSLP), Denver, USA. [find](https://scholar.google.com/scholar?q=Alan+W%2E+Black%2C+Ralf+D%2E+Brown%2C+Robert+Frederking%2C+Kevin+Lenzo%2C+John+Moody%2C+Alexander+Rudnicky%2C+Rita+Singh%2C+and+Eric+Steinbrecher%2E+2002%2E+Rapid+Development+of+Speech%2Dto%2DSpeech+Translation+Systems%2E+In+Int)
20. Long Duong, Antonios Anastasopoulos, David Chiang, Steven Bird, and Trevor Cohn. 2016. An Attentional Model for Speech Translation Without Transcription. In North American Chapter of the Association for Computational Linguistics (NAACL), pages 949–959, San Diego, USA. [find](https://scholar.google.com/scholar?q=Long+Duong%2C+Antonios+Anastasopoulos%2C+David+Chiang%2C+Steven+Bird%2C+and+Trevor+Cohn%2E+2016%2E+An+Attentional+Model+for+Speech+Translation+Without+Transcription%2E+In+North+American+Chapter+of+the+Association+f)
21. Marcely Zanon Boito, William N. Havard, Mahault Garnerin, Éric Le Ferrand, and Laurent Besacier. 2020. MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible. In Language Resources and Evaluation (LREC), Marseille, France. [find](https://scholar.google.com/scholar?q=Marcely+Zanon+Boito%2C+William+N%2E+Havard%2C+Mahault+Garnerin%2C+E%CC%81ric+Le+Ferrand%2C+and+Laurent+Besacier%2E+2020%2E+MaSS%3A+A+Large+and+Clean+Multilingual+Corpus+of+Sentence%2Daligned+Spoken+Utterances+Extracted+from)
22. Marcello Federico, Robert Enyedi, and Roberto Barra-chicote. 2020. From Speech-to-Speech Translation to Automatic Dubbing. arXiv:2001.06785v3. [find](https://scholar.google.com/scholar?q=Marcello+Federico%2C+Robert+Enyedi%2C+and+Roberto+Barra%2Dchicote%2E+2020%2E+From+Speech%2Dto%2DSpeech+Translation+to+Automatic+Dubbing%2E+arXiv%3A2001%2E06785v3%2E)
23. Francisco Casacuberta, Hermann Ney, Franz Josef Och, Enrique Vidal, J. M. Vilar, S. Barrachina, I. Garcı́a-Varea, D. Llorens, C. Martı́nez, S. Molau, F. Nevado, M. Pastor, D. Picó, A. Sanchis, and C. Tillmann. 2004. Some approaches to statistical and finite-state speech-to-speech translation. Compu… [find](https://scholar.google.com/scholar?q=Francisco+Casacuberta%2C+Hermann+Ney%2C+Franz+Josef+Och%2C+Enrique+Vidal%2C+J%2E+M%2E+Vilar%2C+S%2E+Barrachina%2C+I%2E+Garc%C4%B1%CC%81a%2DVarea%2C+D%2E+Llorens%2C+C%2E+Mart%C4%B1%CC%81nez%2C+S%2E+Molau%2C+F%2E+Nevado%2C+M%2E+Pastor%2C+D%2E+Pico%CC%81%2C+A%2E+Sanchis%2C+and+C%2E)
24. Qiao Cheng, Meiyuan Fang, Yaqian Han, Jin Huang, and Yitao Duan. 2019. Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training. In International Workshop on Spoken Language Translation (IWSLT), Hongkong. [find](https://scholar.google.com/scholar?q=Qiao+Cheng%2C+Meiyuan+Fang%2C+Yaqian+Han%2C+Jin+Huang%2C+and+Yitao+Duan%2E+2019%2E+Breaking+the+Data+Barrier%3A+Towards+Robust+Speech+Translation+via+Adversarial+Stability+Training%2E+In+International+Workshop+on+Spo)
25. Yong Cheng, Zhaopeng Tu, Fandong Meng, Junjie Zhai, and Yang Liu. 2018. Towards Robust Neural Machine Translation. In Association for Computational Linguistic (ACL), Melbourne, Australia. [our card](https://md.research.elamur.ai/free/en/papers/cheng-2018-robust-neural-machine-translation/)
26. Eunah Cho, Christian Fügen, Teresa Hermann, Kevin Kilgour, Mohammed Mediani, Christian Mohr, Jan Niehues, Kay Rottmann, Christian Saam, Sebastian Stüker, and Alex Waibel. 2013. A real-world system for simultaneous translation of German lectures. In Annual Conference of the International Speech Com… [find](https://scholar.google.com/scholar?q=Eunah+Cho%2C+Christian+Fu%CC%88gen%2C+Teresa+Hermann%2C+Kevin+Kilgour%2C+Mohammed+Mediani%2C+Christian+Mohr%2C+Jan+Niehues%2C+Kay+Rottmann%2C+Christian+Saam%2C+Sebastian+Stu%CC%88ker%2C+and+Alex+Waibel%2E+2013%2E+A+real%2Dworld+system+f)
27. Hoang Cuong and Khalil Sima’an. 2018. A survey of domain adaptation for statistical machine translation. In Conference on Computational Linguistics (COL-ING), Santa Fe, USA. [find](https://scholar.google.com/scholar?q=Hoang+Cuong+and+Khalil+Sima%E2%80%99an%2E+2018%2E+A+survey+of+domain+adaptation+for+statistical+machine+translation%2E+In+Conference+on+Computational+Linguistics+%28COL%2DING%29%2C+Santa+Fe%2C+USA%2E)
28. Mattia Antonino Di Gangi, Viet-Nhat Nguyen, Matteo Negri, and Marco Turchi. 2020. [find](https://scholar.google.com/scholar?q=Mattia+Antonino+Di+Gangi%2C+Viet%2DNhat+Nguyen%2C+Matteo+Negri%2C+and+Marco+Turchi%2E+2020%2E)
29. Instance-Based Erin Fitzgerald, Keith Hall, and Frederick Jelinek. 2009. Reconstructing false start errors in spontaneous speech text. In European Chapter of the Association for Computational Linguistics (EACL), pages 255–263, Athens, Greece. [find](https://scholar.google.com/scholar?q=Instance%2DBased+Erin+Fitzgerald%2C+Keith+Hall%2C+and+Frederick+Jelinek%2E+2009%2E+Reconstructing+false+start+errors+in+spontaneous+speech+text%2E+In+European+Chapter+of+the+Association+for+Computational+Linguist)
30. Christian Fügen. 2008. A System for Simultaneous Translation of Lectures and Speeches. Ph.D. thesis, University of Karlsruhe. [find](https://scholar.google.com/scholar?q=Christian+Fu%CC%88gen%2E+2008%2E+A+System+for+Simultaneous+Translation+of+Lectures+and+Speeches%2E+Ph%2ED%2E+thesis%2C+University+of+Karlsruhe%2E)
31. Antonino Mattia di Gangi, Roldano Cattoni, Luisa Bentivogli, Matteo Negri, and Marco Turchi. 2019a. MuST-C : a Multilingual Speech Translation Corpus. In North American Chapter of the Association for Computational Linguistics (NAACL), Minneapolis, USA. [our card](https://md.research.elamur.ai/free/en/papers/gangi-2019-must-c-multilingual-speech-translation/)
32. Mattia A. di Gangi, Matteo Negri, Roldano Cattoni, Roberto Dessi, and Marco Turchi. 2019b. Enhancing Transformer for End-to-end Speech-to-Text Translation. In Machine Translation Summit XVII Volume 1: Research Track, pages 21–31, Dublin, Ireland. [find](https://scholar.google.com/scholar?q=Mattia+A%2E+di+Gangi%2C+Matteo+Negri%2C+Roldano+Cattoni%2C+Roberto+Dessi%2C+and+Marco+Turchi%2E+2019b%2E+Enhancing+Transformer+for+End%2Dto%2Dend+Speech%2Dto%2DText+Translation%2E+In+Machine+Translation+Summit+XVII+Volume+1%3A)
33. Mattia Antonino di Gangi, Matteo Negri, and Marco Turchi. 2019c. One-to-Many Multilingual End-to-End Speech Translation. In Automatic Speech Recognition & Understanding (ASRU), December. [find](https://scholar.google.com/scholar?q=Mattia+Antonino+di+Gangi%2C+Matteo+Negri%2C+and+Marco+Turchi%2E+2019c%2E+One%2Dto%2DMany+Multilingual+End%2Dto%2DEnd+Speech+Translation%2E+In+Automatic+Speech+Recognition+%26+Understanding+%28ASRU%29%2C+December%2E)
34. Pierre Godard, Gilles Adda, Martine Adda-Decker, J. Benjumea, L. Besacier, J. Cooper-Leavitt, G-N. Kouarata, L. Lamel, H. Maynard, M. Mueller, A. Rialland, S. Stueker, F. Yvon, and M. Zanon-Boito. 2018. A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments.… [find](https://scholar.google.com/scholar?q=Pierre+Godard%2C+Gilles+Adda%2C+Martine+Adda%2DDecker%2C+J%2E+Benjumea%2C+L%2E+Besacier%2C+J%2E+Cooper%2DLeavitt%2C+G%2DN%2E+Kouarata%2C+L%2E+Lamel%2C+H%2E+Maynard%2C+M%2E+Mueller%2C+A%2E+Rialland%2C+S%2E+Stueker%2C+F%2E+Yvon%2C+and+M%2E+Zanon%2DBoito%2E+201)
35. He He, Jordan Boyd-Graber, and Hal. 2016. Interpretese vs. Translationese : The Uniqueness of Human Strategies in Simultaneous Interpretation. In North American Chapter of the Association for Computational Linguistics (NAACL), pages 971–976, San Diego, USA. [find](https://scholar.google.com/scholar?q=He+He%2C+Jordan+Boyd%2DGraber%2C+and+Hal%2E+2016%2E+Interpretese+vs%2E+Translationese+%3A+The+Uniqueness+of+Human+Strategies+in+Simultaneous+Interpretation%2E+In+North+American+Chapter+of+the+Association+for+Computat)
36. Xiaodong He, Li Deng, and Alex Acero. 2011. Why word error rate is not a good metric for speech recognizer training for the speech translation task? In International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5632–5635, Prague, Czech Republic. [find](https://scholar.google.com/scholar?q=Xiaodong+He%2C+Li+Deng%2C+and+Alex+Acero%2E+2011%2E+Why+word+error+rate+is+not+a+good+metric+for+speech+recognizer+training+for+the+speech+translation+task%3F+In+International+Conference+on+Acoustics%2C+Speech+an)
37. Roger Hsiao, Ashish Venugopal, Thilo Köhler, Ting Zhang, Paisarn Charoenpornsawat, Andreas Zollmann, Stephan Vogel, Alan W. Black, Tanja Schultz, and Alex Waibel. 2006. Optimizing components for handheld two-way speech translation for an English-Iraqi Arabic system. In Annual Conference of the Inte… [find](https://scholar.google.com/scholar?q=Roger+Hsiao%2C+Ashish+Venugopal%2C+Thilo+Ko%CC%88hler%2C+Ting+Zhang%2C+Paisarn+Charoenpornsawat%2C+Andreas+Zollmann%2C+Stephan+Vogel%2C+Alan+W%2E+Black%2C+Tanja+Schultz%2C+and+Alex+Waibel%2E+2006%2E+Optimizing+components+for+hand)
38. Hirofumi Inaguma, Kevin Duh, Tatsuya Kawahara, and Shinji Watanabe. 2019. Multilingual End-to-End Speech Translation. In Automatic Speech Recognition & Understanding (ASRU), Singapore. [find](https://scholar.google.com/scholar?q=Hirofumi+Inaguma%2C+Kevin+Duh%2C+Tatsuya+Kawahara%2C+and+Shinji+Watanabe%2E+2019%2E+Multilingual+End%2Dto%2DEnd+Speech+Translation%2E+In+Automatic+Speech+Recognition+%26+Understanding+%28ASRU%29%2C+Singapore%2E)
39. Sathish Indurthi, Houjeung Han, Nikhil Kumar Lakumarapu, Beomseok Lee, Insoo Chung, Sangha Kim, and Chanwoo Kim. 2020. Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning. In Conference on Artificial Intelligence (AAAI), New York City, USA. [find](https://scholar.google.com/scholar?q=Sathish+Indurthi%2C+Houjeung+Han%2C+Nikhil+Kumar+Lakumarapu%2C+Beomseok+Lee%2C+Insoo+Chung%2C+Sangha+Kim%2C+and+Chanwoo+Kim%2E+2020%2E+Data+Efficient+Direct+Speech%2Dto%2DText+Translation+with+Modality+Agnostic+Meta%2DLear)
40. Javier Iranzo-Sánchez, Joan Albert Silvestre-Cerdà, Javier Jorge, Nahuel Roselló, Adrià Giménez, Albert Sanchis, Jorge Civera, and Alfons Juan. 2020. Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates. In International Conference on Acoustics, Speech and Signal P… [find](https://scholar.google.com/scholar?q=Javier+Iranzo%2DSa%CC%81nchez%2C+Joan+Albert+Silvestre%2DCerda%CC%80%2C+Javier+Jorge%2C+Nahuel+Rosello%CC%81%2C+Adria%CC%80+Gime%CC%81nez%2C+Albert+Sanchis%2C+Jorge+Civera%2C+and+Alfons+Juan%2E+2020%2E+Europarl%2DST%3A+A+Multilingual+Corpus+For+Speech)
41. Ye Jia, Melvin Johnson, Wolfgang Macherey, Ron J Weiss, Yuan Cao, Chung-cheng Chiu Naveen, Ari Stella, and Laurenzo Yonghui. 2019a. Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), Bri… [find](https://scholar.google.com/scholar?q=Ye+Jia%2C+Melvin+Johnson%2C+Wolfgang+Macherey%2C+Ron+J+Weiss%2C+Yuan+Cao%2C+Chung%2Dcheng+Chiu+Naveen%2C+Ari+Stella%2C+and+Laurenzo+Yonghui%2E+2019a%2E+Leveraging+Weakly+Supervised+Data+to+Improve+End%2Dto%2DEnd+Speech%2Dto%2DTe)
42. Ye Jia, Ron J. Weiss, Fadi Biadsy, Wolfgang Macherey, Melvin Johnson, Zhifeng Chen, and Yonghui Wu. 2019b. Direct speech-to-speech translation with a sequence-to-sequence model. In Annual Conference of the International Speech Communication Association (InterSpeech), Graz, Austria. [find](https://scholar.google.com/scholar?q=Ye+Jia%2C+Ron+J%2E+Weiss%2C+Fadi+Biadsy%2C+Wolfgang+Macherey%2C+Melvin+Johnson%2C+Zhifeng+Chen%2C+and+Yonghui+Wu%2E+2019b%2E+Direct+speech%2Dto%2Dspeech+translation+with+a+sequence%2Dto%2Dsequence+model%2E+In+Annual+Conference+o)
43. Jie Jiang, Zeeshan Ahmed, Julie Carson-Berndsen, Peter Cahill, and Andy Way. 2011. Phonetic Representation-Based Speech Translation. In Machine Translation Summit (MTS), pages 81–88, Xiamen, China. [find](https://scholar.google.com/scholar?q=Jie+Jiang%2C+Zeeshan+Ahmed%2C+Julie+Carson%2DBerndsen%2C+Peter+Cahill%2C+and+Andy+Way%2E+2011%2E+Phonetic+Representation%2DBased+Speech+Translation%2E+In+Machine+Translation+Summit+%28MTS%29%2C+pages+81%E2%80%9388%2C+Xiamen%2C+China%2E)
44. Denis Jouvet. 2019. Speech Processing and Prosody. In International Conference of Text, Speech and Dialogue (TSD), Ljubljana, Slovenia. [find](https://scholar.google.com/scholar?q=Denis+Jouvet%2E+2019%2E+Speech+Processing+and+Prosody%2E+In+International+Conference+of+Text%2C+Speech+and+Dialogue+%28TSD%29%2C+Ljubljana%2C+Slovenia%2E)
45. Takatomo Kano, Sakriani Sakti, and Satoshi Nakamura. 2017. Structured-based Curriculum Learning for End-to-end English-Japanese Speech Translation. In Annual Conference of the International Speech Communication Association (InterSpeech), pages 2630–2634. [find](https://scholar.google.com/scholar?q=Takatomo+Kano%2C+Sakriani+Sakti%2C+and+Satoshi+Nakamura%2E+2017%2E+Structured%2Dbased+Curriculum+Learning+for+End%2Dto%2Dend+English%2DJapanese+Speech+Translation%2E+In+Annual+Conference+of+the+International+Speech+Com)
46. Takatomo Kano, Shinnosuke Takamichi, Sakriani Sakti, Graham Neubig, Tomoki Toda, and Satoshi Nakamura. 2018. End to end Model for Cross-Lingual Transformation of Paralinguistic Information. Machine Translation, 32(4):353–368. [find](https://scholar.google.com/scholar?q=Takatomo+Kano%2C+Shinnosuke+Takamichi%2C+Sakriani+Sakti%2C+Graham+Neubig%2C+Tomoki+Toda%2C+and+Satoshi+Nakamura%2E+2018%2E+End+to+end+Model+for+Cross%2DLingual+Transformation+of+Paralinguistic+Information%2E+Machine+Tr)
47. Ali Can Kocabiyikoglu, Laurent Besacier, and Olivier Kraif. 2018. Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation. In Language Resources and Evaluation (LREC), Miyazaki, Japan. [find](https://scholar.google.com/scholar?q=Ali+Can+Kocabiyikoglu%2C+Laurent+Besacier%2C+and+Olivier+Kraif%2E+2018%2E+Augmenting+Librispeech+with+French+Translations%3A+A+Multimodal+Corpus+for+Direct+Speech+Translation+Evaluation%2E+In+Language+Resources+a)
48. Wouter M. Kouw and Marco Loog. 2018. An introduction to domain adaptation and transfer learning. Technical report, Delft University of Technology, Delft, Netherlands. [find](https://scholar.google.com/scholar?q=Wouter+M%2E+Kouw+and+Marco+Loog%2E+2018%2E+An+introduction+to+domain+adaptation+and+transfer+learning%2E+Technical+report%2C+Delft+University+of+Technology%2C+Delft%2C+Netherlands%2E)
49. Alon Lavie, Donna Gates, Marsal Gavalda, Laura Mayfield, Alex Waibel, and Lori Levin. 1996. Multilingual Translation of Spontaneously Spoken Language in a Limited Domain. In International Conference on Computational Linguistics, pages 252–255, Copenhagen, Denmark. [find](https://scholar.google.com/scholar?q=Alon+Lavie%2C+Donna+Gates%2C+Marsal+Gavalda%2C+Laura+Mayfield%2C+Alex+Waibel%2C+and+Lori+Levin%2E+1996%2E+Multilingual+Translation+of+Spontaneously+Spoken+Language+in+a+Limited+Domain%2E+In+International+Conference+o)
50. Robin J Lickley. 1994. Detecting disfluency in spontaneous speech. Ph.D. thesis, University of Edinburgh. [find](https://scholar.google.com/scholar?q=Robin+J+Lickley%2E+1994%2E+Detecting+disfluency+in+spontaneous+speech%2E+Ph%2ED%2E+thesis%2C+University+of+Edinburgh%2E)
51. Fu-hua Liu, Liang Gu, Yuqing Gao, and Michael Picheny. 2003. Use of Statistical N-Gram Models in Natural Language Generation for Machine Translation. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 636– 639, Hongkong. [find](https://scholar.google.com/scholar?q=Fu%2Dhua+Liu%2C+Liang+Gu%2C+Yuqing+Gao%2C+and+Michael+Picheny%2E+2003%2E+Use+of+Statistical+N%2DGram+Models+in+Natural+Language+Generation+for+Machine+Translation%2E+In+International+Conference+on+Acoustics%2C+Speech+a)
52. Yuchen Liu, Hao Xiong, Zhongjun He, Jiajun Zhang, Hua Wu, Haifeng Wang, and Chengqing Zong. 2019. End-to-End Speech Translation with Knowledge Distillation. In Annual Conference of the International Speech Communication Association (Inter-Speech), Graz, Austria. [find](https://scholar.google.com/scholar?q=Yuchen+Liu%2C+Hao+Xiong%2C+Zhongjun+He%2C+Jiajun+Zhang%2C+Hua+Wu%2C+Haifeng+Wang%2C+and+Chengqing+Zong%2E+2019%2E+End%2Dto%2DEnd+Speech+Translation+with+Knowledge+Distillation%2E+In+Annual+Conference+of+the+International+S)
53. Evgeny Matusov, Björn Hoffmeister, and Hermann Ney. 2008. ASR word lattice translation with exhaustive reordering is possible. In Annual Conference of the International Speech Communication Association (InterSpeech), pages 2342–2345, Brisbane, Australia. [find](https://scholar.google.com/scholar?q=Evgeny+Matusov%2C+Bjo%CC%88rn+Hoffmeister%2C+and+Hermann+Ney%2E+2008%2E+ASR+word+lattice+translation+with+exhaustive+reordering+is+possible%2E+In+Annual+Conference+of+the+International+Speech+Communication+Associati)
54. Evgeny Matusov, Arne Mauser, and Hermann Ney. 2006. Automatic Sentence Segmentation and Punctuation Prediction for Spoken Language Translation. In International Workshop on Spoken Language Translation (IWSLT), pages 158–165, Kyoto, Japan. [find](https://scholar.google.com/scholar?q=Evgeny+Matusov%2C+Arne+Mauser%2C+and+Hermann+Ney%2E+2006%2E+Automatic+Sentence+Segmentation+and+Punctuation+Prediction+for+Spoken+Language+Translation%2E+In+International+Workshop+on+Spoken+Language+Translation)
55. Evgeny Matusov, Hermann Ney, and Ralph Schluter. 2005. Phrase-based translation of speech recognizer word lattices using loglinear model combination. In Automatic Speech Recognition and Understanding (ASRU), pages 110–115, San Juan, Puerto Rico. [find](https://scholar.google.com/scholar?q=Evgeny+Matusov%2C+Hermann+Ney%2C+and+Ralph+Schluter%2E+2005%2E+Phrase%2Dbased+translation+of+speech+recognizer+word+lattices+using+loglinear+model+combination%2E+In+Automatic+Speech+Recognition+and+Understanding+)
56. Evgeny Matusov, Patrick Wilken, and Yota Georgakopoulou. 2019. Customizing Neural Machine Translation for Subtitling. In Conference on Machine Translation (WMT), pages 82–93, Florence, Italy. [find](https://scholar.google.com/scholar?q=Evgeny+Matusov%2C+Patrick+Wilken%2C+and+Yota+Georgakopoulou%2E+2019%2E+Customizing+Neural+Machine+Translation+for+Subtitling%2E+In+Conference+on+Machine+Translation+%28WMT%29%2C+pages+82%E2%80%9393%2C+Florence%2C+Italy%2E)
57. Peter Newmark. 1988. Approaches to Translation. Prentice Hall, Hertfordshire. [find](https://scholar.google.com/scholar?q=Peter+Newmark%2E+1988%2E+Approaches+to+Translation%2E+Prentice+Hall%2C+Hertfordshire%2E)
58. Hermann Ney. 1999. Speech Translation: Coupling of Recognition and Translation. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 517–520, Phoenix, USA. [find](https://scholar.google.com/scholar?q=Hermann+Ney%2E+1999%2E+Speech+Translation%3A+Coupling+of+Recognition+and+Translation%2E+In+International+Conference+on+Acoustics%2C+Speech%2C+and+Signal+Processing+%28ICASSP%29%2C+pages+517%E2%80%93520%2C+Phoenix%2C+USA%2E)
59. Jan Niehues, Roldano Cattoni, Sebastian Stüker, Matteo Negri, Marco Turchi, Thanh-Le Ha, Elizabeth Salesky, Ramon Sanabria, Loic Barrault, Lucia Specia, and Marcello Federico. 2019. [find](https://scholar.google.com/scholar?q=Jan+Niehues%2C+Roldano+Cattoni%2C+Sebastian+Stu%CC%88ker%2C+Matteo+Negri%2C+Marco+Turchi%2C+Thanh%2DLe+Ha%2C+Elizabeth+Salesky%2C+Ramon+Sanabria%2C+Loic+Barrault%2C+Lucia+Specia%2C+and+Marcello+Federico%2E+2019%2E)
60. The IWSLT 2019 Evaluation Campaign. In International Workshop on Spoken Language Translation (IWSLT), Hongkong. [find](https://scholar.google.com/scholar?q=The+IWSLT+2019+Evaluation+Campaign%2E+In+International+Workshop+on+Spoken+Language+Translation+%28IWSLT%29%2C+Hongkong%2E)
61. Jan Niehues, Ngoc-Quan Pham, Thanh-Le Ha, Matthias Sperber, and Alex Waibel. 2018. Low-Latency Neural Speech Translation. In Annual Conference of the International Speech Communication Association (InterSpeech), Hyderabad, India. [find](https://scholar.google.com/scholar?q=Jan+Niehues%2C+Ngoc%2DQuan+Pham%2C+Thanh%2DLe+Ha%2C+Matthias+Sperber%2C+and+Alex+Waibel%2E+2018%2E+Low%2DLatency+Neural+Speech+Translation%2E+In+Annual+Conference+of+the+International+Speech+Communication+Association+%28In)
62. Matthias Paulik. 2010. Learning Speech Translation from Interpretation. Ph.D. thesis, University of Karlsruhe. [find](https://scholar.google.com/scholar?q=Matthias+Paulik%2E+2010%2E+Learning+Speech+Translation+from+Interpretation%2E+Ph%2ED%2E+thesis%2C+University+of+Karlsruhe%2E)
63. Stephan Peitz, Simon Wiesler, Markus Nussbaum-Thom, and Hermann Ney. 2012. Spoken Language Translation Using Automatically Transcribed Text in Training. In International Workshop on Spoken Language Translation (IWSLT) 2011, pages 276– 283, Hongkong. [find](https://scholar.google.com/scholar?q=Stephan+Peitz%2C+Simon+Wiesler%2C+Markus+Nussbaum%2DThom%2C+and+Hermann+Ney%2E+2012%2E+Spoken+Language+Translation+Using+Automatically+Transcribed+Text+in+Training%2E+In+International+Workshop+on+Spoken+Language+Tr)
64. Matt Post, Gaurav Kumar, Adam Lopez, Damianos Karakos, Chris Callison-Burch, and Sanjeev Khudanpur. 2013. Improved Speech-to-Text Translation with the Fisher and Callhome Spanish–English Speech Translation Corpus. In International Workshop on Spoken Language Translation (IWSLT), Heidelberg, Germany. [find](https://scholar.google.com/scholar?q=Matt+Post%2C+Gaurav+Kumar%2C+Adam+Lopez%2C+Damianos+Karakos%2C+Chris+Callison%2DBurch%2C+and+Sanjeev+Khudanpur%2E+2013%2E+Improved+Speech%2Dto%2DText+Translation+with+the+Fisher+and+Callhome+Spanish%E2%80%93English+Speech+Transl)
65. Pablo Romero-Fresco. 2009. More haste less speed: Edited versus verbatim respoken subtitles. Vigo International Journal of Applied Linguistics, 6:109– 134. [find](https://scholar.google.com/scholar?q=Pablo+Romero%2DFresco%2E+2009%2E+More+haste+less+speed%3A+Edited+versus+verbatim+respoken+subtitles%2E+Vigo+International+Journal+of+Applied+Linguistics%2C+6%3A109%E2%80%93+134%2E)
66. Nicholas Ruiz and Marcello Federico. 2014. Assessing the impact of speech recognition errors on machine translation quality. Conference of the Association for Machine Translation in the Americas (AMTA), 1(November):261–274. [find](https://scholar.google.com/scholar?q=Nicholas+Ruiz+and+Marcello+Federico%2E+2014%2E+Assessing+the+impact+of+speech+recognition+errors+on+machine+translation+quality%2E+Conference+of+the+Association+for+Machine+Translation+in+the+Americas+%28AMTA)
67. Nicholas Ruiz, Qin Gao, William Lewis, and Marcello Federico. 2015. Adapting Machine Translation Models toward Misrecognized Speech with Text-to-Speech Pronunciation Rules and Acoustic Confusability. In Annual Conference of the International Speech Communication Association (Inter-Speech), pages 224… [find](https://scholar.google.com/scholar?q=Nicholas+Ruiz%2C+Qin+Gao%2C+William+Lewis%2C+and+Marcello+Federico%2E+2015%2E+Adapting+Machine+Translation+Models+toward+Misrecognized+Speech+with+Text%2Dto%2DSpeech+Pronunciation+Rules+and+Acoustic+Confusability%2E+)
68. Ashutosh Saboo and Timo Baumann. 2019. Integration of Dubbing Constraints into Machine Translation. In Conference on Machine Translation (WMT), pages 94–101, Florence, Italy. [find](https://scholar.google.com/scholar?q=Ashutosh+Saboo+and+Timo+Baumann%2E+2019%2E+Integration+of+Dubbing+Constraints+into+Machine+Translation%2E+In+Conference+on+Machine+Translation+%28WMT%29%2C+pages+94%E2%80%93101%2C+Florence%2C+Italy%2E)
69. Shirin Saleem, Szu-Chen Jou, Stephan Vogel, and Tanja Schultz. 2004. Using Word Lattice Information for a Tighter Coupling in Speech Translation Systems. In International Conference on Spoken Language Processing (ICSLP), pages 41–44, Jeju Island, Korea. [find](https://scholar.google.com/scholar?q=Shirin+Saleem%2C+Szu%2DChen+Jou%2C+Stephan+Vogel%2C+and+Tanja+Schultz%2E+2004%2E+Using+Word+Lattice+Information+for+a+Tighter+Coupling+in+Speech+Translation+Systems%2E+In+International+Conference+on+Spoken+Language)
70. Elizabeth Salesky, Matthias Sperber, and Alan W Black. 2019a. Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation. In Association for Computational Linguistics (ACL), pages 1835–1841, Florence, Italy. [find](https://scholar.google.com/scholar?q=Elizabeth+Salesky%2C+Matthias+Sperber%2C+and+Alan+W+Black%2E+2019a%2E+Exploring+Phoneme%2DLevel+Speech+Representations+for+End%2Dto%2DEnd+Speech+Translation%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2C+page)
71. Alicia Pérez, Victor Guijarrubia, Raquel Justo, M. Inés Torres, and Francisco Casacuberta. 2007. A comparison of linguistically and statistically enhanced models for speech-to-speech machine translation. In International Workshop on Spoken Language Translation (IWSLT), Trento, Italy. [find](https://scholar.google.com/scholar?q=Alicia+Pe%CC%81rez%2C+Victor+Guijarrubia%2C+Raquel+Justo%2C+M%2E+Ine%CC%81s+Torres%2C+and+Francisco+Casacuberta%2E+2007%2E+A+comparison+of+linguistically+and+statistically+enhanced+models+for+speech%2Dto%2Dspeech+machine+transla)
72. Elizabeth Salesky, Matthias Sperber, and Alex Waibel. 2019b. Fluent Translations from Disfluent Speech in End-to-End Speech Translation. In North American Chapter of the Association for Computational Linguistics (NAACL), Minneapolis, USA. [find](https://scholar.google.com/scholar?q=Elizabeth+Salesky%2C+Matthias+Sperber%2C+and+Alex+Waibel%2E+2019b%2E+Fluent+Translations+from+Disfluent+Speech+in+End%2Dto%2DEnd+Speech+Translation%2E+In+North+American+Chapter+of+the+Association+for+Computational+)
73. Ngoc-quan Pham, Thai-son Nguyen, Thanh-Le Ha, Juan Hussain, Felix Schneider, Jan Niehues, Sebastian Stüker, and Alexander Waibel. 2019. [find](https://scholar.google.com/scholar?q=Ngoc%2Dquan+Pham%2C+Thai%2Dson+Nguyen%2C+Thanh%2DLe+Ha%2C+Juan+Hussain%2C+Felix+Schneider%2C+Jan+Niehues%2C+Sebastian+Stu%CC%88ker%2C+and+Alexander+Waibel%2E+2019%2E)
74. The IWSLT 2019 KIT Speech Translation System. In International Workshop on Spoken Language Translation (IWSLT), Hongkong. [find](https://scholar.google.com/scholar?q=The+IWSLT+2019+KIT+Speech+Translation+System%2E+In+International+Workshop+on+Spoken+Language+Translation+%28IWSLT%29%2C+Hongkong%2E)
75. Ramon Sanabria, Ozan Caglayan, Shruti Palaskar, Desmond Elliott, Loı̈c Barrault, Lucia Specia, and Florian Metze. 2018. How2: a large-scale dataset for multimodal language understanding. In Workshop on Visually Grounded Interaction and Language (ViGIL). NeurIPS. [find](https://scholar.google.com/scholar?q=Ramon+Sanabria%2C+Ozan+Caglayan%2C+Shruti+Palaskar%2C+Desmond+Elliott%2C+Lo%C4%B1%CC%88c+Barrault%2C+Lucia+Specia%2C+and+Florian+Metze%2E+2018%2E+How2%3A+a+large%2Dscale+dataset+for+multimodal+language+understanding%2E+In+Workshop+o)
76. Juan Pino, Liezl Puzon, Jiatao Gu, Xutai Ma, Arya D. McCarthy, and Deepak Gopinath. 2019. Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade. In International Workshop on Spoken Language Translation (IWSLT), Hongkong. [find](https://scholar.google.com/scholar?q=Juan+Pino%2C+Liezl+Puzon%2C+Jiatao+Gu%2C+Xutai+Ma%2C+Arya+D%2E+McCarthy%2C+and+Deepak+Gopinath%2E+2019%2E+Harnessing+Indirect+Training+Data+for+End%2Dto%2DEnd+Automatic+Speech+Translation%3A+Tricks+of+the+Trade%2E+In+Interna)
77. Matthias Sperber, Graham Neubig, Jan Niehues, and Alex Waibel. 2017a. Neural Lattice-to-Sequence Models for Uncertain Inputs. In Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1380–1389, Copenhagen, Denmark. [find](https://scholar.google.com/scholar?q=Matthias+Sperber%2C+Graham+Neubig%2C+Jan+Niehues%2C+and+Alex+Waibel%2E+2017a%2E+Neural+Lattice%2Dto%2DSequence+Models+for+Uncertain+Inputs%2E+In+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C)
78. Matthias Sperber, Graham Neubig, Jan Niehues, and Alex Waibel. 2019a. Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation. Transactions of the Association for Computational Linguistics (TACL). [find](https://scholar.google.com/scholar?q=Matthias+Sperber%2C+Graham+Neubig%2C+Jan+Niehues%2C+and+Alex+Waibel%2E+2019a%2E+Attention%2DPassing+Models+for+Robust+and+Data%2DEfficient+End%2Dto%2DEnd+Speech+Translation%2E+Transactions+of+the+Association+for+Computat)
79. Matthias Sperber, Graham Neubig, Ngoc-Quan Pham, and Alex Waibel. 2019b. Self-Attentional Models for Lattice Inputs. In Association for Computational Linguistic (ACL), pages 1185–1197, Florence, Italy. [find](https://scholar.google.com/scholar?q=Matthias+Sperber%2C+Graham+Neubig%2C+Ngoc%2DQuan+Pham%2C+and+Alex+Waibel%2E+2019b%2E+Self%2DAttentional+Models+for+Lattice+Inputs%2E+In+Association+for+Computational+Linguistic+%28ACL%29%2C+pages+1185%E2%80%931197%2C+Florence%2C+Italy)
80. Matthias Sperber, Jan Niehues, and Alex Waibel. 2017b. Toward Robust Neural Machine Translation for Noisy Input Sequences. In International Workshop on Spoken Language Translation (IWSLT), Tokyo, Japan. [find](https://scholar.google.com/scholar?q=Matthias+Sperber%2C+Jan+Niehues%2C+and+Alex+Waibel%2E+2017b%2E+Toward+Robust+Neural+Machine+Translation+for+Noisy+Input+Sequences%2E+In+International+Workshop+on+Spoken+Language+Translation+%28IWSLT%29%2C+Tokyo%2C+Japa)
81. F. W. M. Stentiford and M. G. Steer. 1988. Machine Translation of Speech. British Telecom technology journal, 6(2):116–123. [find](https://scholar.google.com/scholar?q=F%2E+W%2E+M%2E+Stentiford+and+M%2E+G%2E+Steer%2E+1988%2E+Machine+Translation+of+Speech%2E+British+Telecom+technology+journal%2C+6%282%29%3A116%E2%80%93123%2E)
82. Mihaela C. Stoian, Sameer Bansal, and Sharon Goldwater. 2020. Analyzing ASR pretraining for low-resource speech-to-text translation. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain. [find](https://scholar.google.com/scholar?q=Mihaela+C%2E+Stoian%2C+Sameer+Bansal%2C+and+Sharon+Goldwater%2E+2020%2E+Analyzing+ASR+pretraining+for+low%2Dresource+speech%2Dto%2Dtext+translation%2E+In+International+Conference+on+Acoustics%2C+Speech+and+Signal+Process)
83. Umut Sulubacak, Ozan Caglayan, Stig-Arne Grönroos, Aku Rouhe, Desmond Elliott, Lucia Specia, and Jörg Tiedemann. 2019. Multimodal Machine Translation through Visuals and Speech. arXiv:1911.12798. — [arXiv:1911.12798](https://arxiv.org/abs/1911.12798) [find](https://scholar.google.com/scholar?q=Umut+Sulubacak%2C+Ozan+Caglayan%2C+Stig%2DArne+Gro%CC%88nroos%2C+Aku+Rouhe%2C+Desmond+Elliott%2C+Lucia+Specia%2C+and+Jo%CC%88rg+Tiedemann%2E+2019%2E+Multimodal+Machine+Translation+through+Visuals+and+Speech%2E+arXiv%3A1911%2E12798%2E+%E2%80%94+)
84. Eiichiro Sumita, Tohru Shimizu, and Satoshi Nakamura. 2007. NICT-ATR speech-to-speech translation system. In Association for Computational Linguistic (ACL), pages 25–28, Prague, Czech Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Eiichiro+Sumita%2C+Tohru+Shimizu%2C+and+Satoshi+Nakamura%2E+2007%2E+NICT%2DATR+speech%2Dto%2Dspeech+translation+system%2E+In+Association+for+Computational+Linguistic+%28ACL%29%2C+pages+25%E2%80%9328%2C+Prague%2C+Czech+Republic%2E+Associ)
85. Enrique Vidal. 1997. Finite-State Speech-to-Speech Translation. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 111–114, Munich, Germany. [find](https://scholar.google.com/scholar?q=Enrique+Vidal%2E+1997%2E+Finite%2DState+Speech%2Dto%2DSpeech+Translation%2E+In+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%28ICASSP%29%2C+pages+111%E2%80%93114%2C+Munich%2C+Germany%2E)
86. Alex Waibel, Ajay N. Jain, Arthur E. McNair, Hiroaki Saito, Alexander G. Hauptmann, and Joe Tebelskis. 1991. JANUS: a speech-to-speech translation system using connectionist and symbolic processing strategies. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 79… [find](https://scholar.google.com/scholar?q=Alex+Waibel%2C+Ajay+N%2E+Jain%2C+Arthur+E%2E+McNair%2C+Hiroaki+Saito%2C+Alexander+G%2E+Hauptmann%2C+and+Joe+Tebelskis%2E+1991%2E+JANUS%3A+a+speech%2Dto%2Dspeech+translation+system+using+connectionist+and+symbolic+processing+st)
87. Changhan Wang, Juan Pino, Anne Wu, and Jiatao Gu. 2020a. CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus. In Language Resources and Evaluation (LREC), Marseille, France. [find](https://scholar.google.com/scholar?q=Changhan+Wang%2C+Juan+Pino%2C+Anne+Wu%2C+and+Jiatao+Gu%2E+2020a%2E+CoVoST%3A+A+Diverse+Multilingual+Speech%2DTo%2DText+Translation+Corpus%2E+In+Language+Resources+and+Evaluation+%28LREC%29%2C+Marseille%2C+France%2E)
88. Chengyi Wang, Yu Wu, Shujie Liu, Zhenglu Yang, and Ming Zhou. 2020b. Bridging the Gap between Pre-Training and Fine-Tuning for End-to-End Speech Translation. In Conference on Artificial Intelligence (AAAI), New York City, USA. [find](https://scholar.google.com/scholar?q=Chengyi+Wang%2C+Yu+Wu%2C+Shujie+Liu%2C+Zhenglu+Yang%2C+and+Ming+Zhou%2E+2020b%2E+Bridging+the+Gap+between+Pre%2DTraining+and+Fine%2DTuning+for+End%2Dto%2DEnd+Speech+Translation%2E+In+Conference+on+Artificial+Intelligence+%28)
89. Ye-Yi Wang and Alex Waibel. 1998. Modeling with structures in statistical machine translation. In Association for Computational Linguistics and International Conference on Computational Linguistics (COLING-ACL), pages 1357–1363, Montréal, Canada. [find](https://scholar.google.com/scholar?q=Ye%2DYi+Wang+and+Alex+Waibel%2E+1998%2E+Modeling+with+structures+in+statistical+machine+translation%2E+In+Association+for+Computational+Linguistics+and+International+Conference+on+Computational+Linguistics+%28C)
90. Ron J. Weiss, Jan Chorowski, Navdeep Jaitly, Yonghui Wu, and Zhifeng Chen. 2017. Sequence-to-Sequence Models Can Directly Transcribe Foreign Speech. In Annual Conference of the International Speech Communication Association (InterSpeech), Stockholm, Sweden. [find](https://scholar.google.com/scholar?q=Ron+J%2E+Weiss%2C+Jan+Chorowski%2C+Navdeep+Jaitly%2C+Yonghui+Wu%2C+and+Zhifeng+Chen%2E+2017%2E+Sequence%2Dto%2DSequence+Models+Can+Directly+Transcribe+Foreign+Speech%2E+In+Annual+Conference+of+the+International+Speech+Co)
91. Tzu-Wei Sung, Jun-You Liu, Hung-yi Lee, and Lin-shan Lee. 2019. Towards End-to-End Speech-to-Text Translation with Two-Pass Decoding. In ICASSP, pages 7175–7179, Brighton, United Kingdom. [find](https://scholar.google.com/scholar?q=Tzu%2DWei+Sung%2C+Jun%2DYou+Liu%2C+Hung%2Dyi+Lee%2C+and+Lin%2Dshan+Lee%2E+2019%2E+Towards+End%2Dto%2DEnd+Speech%2Dto%2DText+Translation+with+Two%2DPass+Decoding%2E+In+ICASSP%2C+pages+7175%E2%80%937179%2C+Brighton%2C+United+Kingdom%2E)
92. M. Woszczyna, N. Coccaro, A. Eisele, A. Lavie, A. Mc-Nair, T. Polzin, I. Rogina, C. P. Rose, T. Sloboda, M. Tomita, J. Tsutsumi, N. Aoki-Waibel, A. Waibel, and W. Ward. 1993. Recent advances in JANUS: A Speech Translation System. In Workshop on Human Language Technology (HLT), pages 211–216, Plainsb… [find](https://scholar.google.com/scholar?q=M%2E+Woszczyna%2C+N%2E+Coccaro%2C+A%2E+Eisele%2C+A%2E+Lavie%2C+A%2E+Mc%2DNair%2C+T%2E+Polzin%2C+I%2E+Rogina%2C+C%2E+P%2E+Rose%2C+T%2E+Sloboda%2C+M%2E+Tomita%2C+J%2E+Tsutsumi%2C+N%2E+Aoki%2DWaibel%2C+A%2E+Waibel%2C+and+W%2E+Ward%2E+1993%2E+Recent+advances+in+JANUS%3A)
93. Toshiyuki Takezawa, Tsuyoshi Morimoto, Yoshinori Sagisaka, Nick Campbell, Hitoshi Iida, Fumiaki Sugaya, Akio Yokoo, and Seiichi Yamamoto. 1998. A Japanese-to-English Speech Translation System: ATR-MATRIX. In International Conference on Spoken Language (ICSLP), Sydney, Australia. [find](https://scholar.google.com/scholar?q=Toshiyuki+Takezawa%2C+Tsuyoshi+Morimoto%2C+Yoshinori+Sagisaka%2C+Nick+Campbell%2C+Hitoshi+Iida%2C+Fumiaki+Sugaya%2C+Akio+Yokoo%2C+and+Seiichi+Yamamoto%2E+1998%2E+A+Japanese%2Dto%2DEnglish+Speech+Translation+System%3A+ATR%2DMAT)
94. Pei Zhang, Boxing Chen, Niyu Ge, and Kai Fan. 2019. Lattice Transformer for Speech Translation. In Association for Computational Linguistic (ACL), pages 6475–6484, Florence, Italy. [find](https://scholar.google.com/scholar?q=Pei+Zhang%2C+Boxing+Chen%2C+Niyu+Ge%2C+and+Kai+Fan%2E+2019%2E+Lattice+Transformer+for+Speech+Translation%2E+In+Association+for+Computational+Linguistic+%28ACL%29%2C+pages+6475%E2%80%936484%2C+Florence%2C+Italy%2E)
95. Andros Tjandra, Sakriani Sakti, and Satoshi Nakamura. 2019. Speech-to-speech Translation between Untranscribed Unknown Languages. In Automatic Speech Recognition & Understanding (ASRU), Singapore. [find](https://scholar.google.com/scholar?q=Andros+Tjandra%2C+Sakriani+Sakti%2C+and+Satoshi+Nakamura%2E+2019%2E+Speech%2Dto%2Dspeech+Translation+between+Untranscribed+Unknown+Languages%2E+In+Automatic+Speech+Recognition+%26+Understanding+%28ASRU%29%2C+Singapore%2E)
96. Ruiqiang Zhang, Genichiro Kikui, Hirofumi Yamamoto, and Wai-Kit Lo. 2005. A Decoding Algorithm for Word Lattice Translation in Speech Translation. In International Workshop on Spoken Language Translation (IWSLT), pages 23–29, Pittsburgh, USA. [find](https://scholar.google.com/scholar?q=Ruiqiang+Zhang%2C+Genichiro+Kikui%2C+Hirofumi+Yamamoto%2C+and+Wai%2DKit+Lo%2E+2005%2E+A+Decoding+Algorithm+for+Word+Lattice+Translation+in+Speech+Translation%2E+In+International+Workshop+on+Spoken+Language+Translat)
97. Yulia Tsvetkov, Florian Metze, and Chris Dyer. 2014. Augmenting translation models with simulated acoustic confusions for improved spoken language translation. In Conference of the European Chapter of the Association for Computational Linguistics (EACL), pages 616–625, Gothenburg, Sweden. [find](https://scholar.google.com/scholar?q=Yulia+Tsvetkov%2C+Florian+Metze%2C+and+Chris+Dyer%2E+2014%2E+Augmenting+translation+models+with+simulated+acoustic+confusions+for+improved+spoken+language+translation%2E+In+Conference+of+the+European+Chapter+of)

*Updated 24 October 2026*