---
title: "MUSCAT: MUltilingual, SCientific — Sinhamahapatra 2026"
description: "MUSCAT is a benchmark that tests whether current automatic speech recognition (ASR) systems can handle realistic multilingual dialogue."
authors: ["Supriti Sinhamahapatra", "Thai-Binh Nguyen", "Yiğit Oğuz", "Enes Yavuz Ugan", "Jan Niehues", "Alexander Waibel"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.471/"
doi: "10.63317/2q8inmh4zmpa"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/sinhamahapatra-2026-muscat-multilingual-scientific-conversation-benchmark/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/sinhamahapatra-2026-muscat-multilingual-scientific-conversation-benchmark/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/3/) / MUSCAT: MUltilingual, SCientific ConversATion Benchmark

# MUSCAT: MUltilingual, SCientific ConversATion Benchmark

**Authors:** [Supriti Sinhamahapatra](https://md.research.elamur.ai/free/authors/supriti-sinhamahapatra/), Thai-Binh Nguyen, Yiğit Oğuz, [Enes Yavuz Ugan](https://md.research.elamur.ai/free/authors/enes-yavuz-ugan/), [Jan Niehues](https://md.research.elamur.ai/free/authors/jan-niehues/), [Alexander Waibel](https://md.research.elamur.ai/free/authors/alexander-waibel/) · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.471/) · [PDF](https://aclanthology.org/2026.lrec-1.471.pdf) · [DOI 10.63317/2q8inmh4zmpa](https://doi.org/10.63317/2q8inmh4zmpa) · [OpenAlex](https://openalex.org/W7160098012)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14) · 1 in our library, of the 140673 papers whose bibliographies we read

## Summary
MUSCAT is a benchmark that tests whether current automatic speech recognition (ASR) systems can handle realistic multilingual dialogue. Until now, no dataset covered this setting. In each conversation, two bilingual researchers discuss a scientific paper they have both read. Each person speaks only one language but understands the other's. This combines several difficulties: mixed-language input, speaker turns, technical vocabulary, code-switching and varied acoustic conditions.

Every session was captured at the same time by three devices: a conference camera, a microphone array and wearable smart glasses. The audio was then aligned by hand. Annotators split the recordings into single-language segments and corrected Whisper drafts to produce transcripts. The speakers did this correction themselves so that technical terms were rendered accurately. They also tagged code-switched words.

The authors ran four ASR baselines with an evaluation protocol that goes beyond WER. The models often miss language switches. They tend to render speech in the language of the preceding context or drop segments entirely. The benchmark therefore remains an open problem for multilingual meeting and translation technology.

## Key points
- **Data size and speakers:** six recordings, eleven speakers (six male, five female) and about 64–65 minutes of audio with 9,066 transcribed words.
- **Language pairs:** English paired with German (about 21 min), Vietnamese (17), Chinese (15) and Turkish (12). Speakers are C1-level in English and native in the other language.
- **Recording devices:** Meeting Owl 3 ("OWL"), a ReSpeaker USB Microphone Array on a Raspberry Pi ("Pi"), and Meta Aria glasses worn by one participant. All recorded at 44.1 kHz.
- **Annotation and variants:** segments were cut in Label Studio, each in a single language and no longer than 30 s. The release includes segmented and unsegmented versions for each device.
- **Baselines and availability:** Whisper, SALMONN, Phi-4 Multimodal and Wav2Vec2 were tested. The dataset is on Hugging Face as `goodpiku/muscat-eval`.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/)

## Cite

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

```bibtex
@inproceedings{sinhamahapatra2026muscat,
  title = {{MUSCAT: MUltilingual, SCientific ConversATion Benchmark}},
  author = {Sinhamahapatra, Supriti and Nguyen, Thai-Binh and Oğuz, Yiğit and Ugan, Enes Yavuz and Niehues, Jan and Waibel, Alexander},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/2q8inmh4zmpa},
  url = {https://doi.org/10.63317/2q8inmh4zmpa}
}
```

- [← previous MultiWikiQA: A Reading Comprehension Benchmark in 300+ Languages](https://md.research.elamur.ai/free/papers/smart-2026-multiwikiqa-reading-comprehension-benchmark-300/)
- [next → MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages](https://md.research.elamur.ai/free/papers/lombard-2026-mzansitext-mzansilm-open-corpus-decoder/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/3/)

## References

56 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdelrahman Abouelenin, Atabak Ashfaq, Adam Atkinson, Hany Awadalla, Nguyen Bach, Jianmin Bao, Alon Benhaim, Martin Cai, Vishrav Chaudhary, Congcong Chen, et al. 2025. Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-loras. arXiv preprint arXiv:2503.01743. [find](https://scholar.google.com/scholar?q=Abdelrahman+Abouelenin%2C+Atabak+Ashfaq%2C+Adam+Atkinson%2C+Hany+Awadalla%2C+Nguyen+Bach%2C+Jianmin+Bao%2C+Alon+Benhaim%2C+Martin+Cai%2C+Vishrav+Chaudhary%2C+Congcong+Chen%2C+et+al%2E+2025%2E+Phi%2D4%2Dmini+technical+report%3A+Com) [our card](https://md.research.elamur.ai/free/papers/microsoft-2025-phi-4-mini-technical-report/)
2. Joshua Ainslie, James Lee-Thorp, Michiel De Jong, Yury Zemlyanskiy, Federico Lebrón, and Sumit Sanghai. 2023. Gqa: Training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:2305.13245. [find](https://scholar.google.com/scholar?q=Joshua+Ainslie%2C+James+Lee%2DThorp%2C+Michiel+De+Jong%2C+Yury+Zemlyanskiy%2C+Federico+Lebr%C3%B3n%2C+and+Sumit+Sanghai%2E+2023%2E+Gqa%3A+Training+generalized+multi%2Dquery+transformer+models+from+multi%2Dhead+checkpoints%2E+arXi) [our card](https://md.research.elamur.ai/free/papers/ainslie-2023-gqa-training-generalized-multi-query/)
3. Rosana Ardila, Megan Branson, Kelly Davis, Michael Henretty, Michael Kohler, Josh Meyer, Reuben Morais, Lindsay Saunders, Francis M Tyers, and Gregor Weber. 2019. Common voice: A massively-multilingual speech corpus. arXiv preprint arXiv:1912.06670. [find](https://scholar.google.com/scholar?q=Rosana+Ardila%2C+Megan+Branson%2C+Kelly+Davis%2C+Michael+Henretty%2C+Michael+Kohler%2C+Josh+Meyer%2C+Reuben+Morais%2C+Lindsay+Saunders%2C+Francis+M+Tyers%2C+and+Gregor+Weber%2E+2019%2E+Common+voice%3A+A+massively%2Dmultilingua) [our card](https://md.research.elamur.ai/free/papers/ardila-2019-common-voice-massively-multilingual-speech/)
4. Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, 33:12449–12460. [find](https://scholar.google.com/scholar?q=Alexei+Baevski%2C+Yuhao+Zhou%2C+Abdelrahman+Mohamed%2C+and+Michael+Auli%2E+2020%2E+wav2vec+2%2E0%3A+A+framework+for+self%2Dsupervised+learning+of+speech+representations%2E+Advances+in+neural+information+processing+syst) [our card](https://md.research.elamur.ai/free/papers/baevski-2020-wav2vec-2-0-framework-self/)
5. Max Bain, Jaesung Huh, Tengda Han, and Andrew Zisserman. 2023. Whisperx: Time-accurate speech transcription of long-form audio. [find](https://scholar.google.com/scholar?q=Max+Bain%2C+Jaesung+Huh%2C+Tengda+Han%2C+and+Andrew+Zisserman%2E+2023%2E+Whisperx%3A+Time%2Daccurate+speech+transcription+of+long%2Dform+audio%2E)
6. Loïc Barrault, Yu-An Chung, Mariano Coria Meglioli, David Dale, Ning Dong, Mark Duppenthaler, Paul-Ambroise Duquenne, Brian Ellis, Hady Elsahar, Justin Haaheim, et al. 2023. Seamless: Multilingual expressive and streaming speech translation. arXiv preprint arXiv:2312.05187. [find](https://scholar.google.com/scholar?q=Lo%C3%AFc+Barrault%2C+Yu%2DAn+Chung%2C+Mariano+Coria+Meglioli%2C+David+Dale%2C+Ning+Dong%2C+Mark+Duppenthaler%2C+Paul%2DAmbroise+Duquenne%2C+Brian+Ellis%2C+Hady+Elsahar%2C+Justin+Haaheim%2C+et+al%2E+2023%2E+Seamless%3A+Multilingual+exp) [our card](https://md.research.elamur.ai/free/papers/communication-2023-seamless-multilingual-expressive-streaming-speech/)
7. Hervé Bredin and Antoine Laurent. 2021. End-to-end speaker segmentation for overlap-aware resegmentation. In Interspeech 2021, pages 3111–3115. [find](https://scholar.google.com/scholar?q=Herv%C3%A9+Bredin+and+Antoine+Laurent%2E+2021%2E+End%2Dto%2Dend+speaker+segmentation+for+overlap%2Daware+resegmentation%2E+In+Interspeech+2021%2C+pages+3111%E2%80%933115%2E)
8. Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Inigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gašić. 2018. Multiwoz–a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling. arXiv preprint arXiv:1810.00278. [find](https://scholar.google.com/scholar?q=Pawe%C5%82+Budzianowski%2C+Tsung%2DHsien+Wen%2C+Bo%2DHsiang+Tseng%2C+Inigo+Casanueva%2C+Stefan+Ultes%2C+Osman+Ramadan%2C+and+Milica+Ga%C5%A1i%C4%87%2E+2018%2E+Multiwoz%E2%80%93a+large%2Dscale+multi%2Ddomain+wizard%2Dof%2Doz+dataset+for+task%2Doriented+d)
9. Sanyuan Chen, Yu Wu, Chengyi Wang, Shujie Liu, Daniel Tompkins, Zhuo Chen, and Furu Wei. 2022. Beats: Audio pre-training with acoustic tokenizers. arXiv preprint arXiv:2212.09058. — [arXiv:2212.09058](https://arxiv.org/abs/2212.09058) [find](https://scholar.google.com/scholar?q=Sanyuan+Chen%2C+Yu+Wu%2C+Chengyi+Wang%2C+Shujie+Liu%2C+Daniel+Tompkins%2C+Zhuo+Chen%2C+and+Furu+Wei%2E+2022%2E+Beats%3A+Audio+pre%2Dtraining+with+acoustic+tokenizers%2E+arXiv+preprint+arXiv%3A2212%2E09058%2E+%E2%80%94+%5BarXiv%3A2212%2E09058%5D)
10. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See [https://vicuna.lmsys](https://vicuna.lmsys). org (accessed 14 April 2023), 2(3):6. [↗](https://vicuna.lmsys)
11. Steven B. Davis and Paul Mermelstein. 1980. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech and Signal Processing, 28(4):357–366. [find](https://scholar.google.com/scholar?q=Steven+B%2E+Davis+and+Paul+Mermelstein%2E+1980%2E+Comparison+of+parametric+representations+for+monosyllabic+word+recognition+in+continuously+spoken+sentences%2E+IEEE+Transactions+on+Acoustics%2C+Speech+and+Sign)
12. Mattia A. Di Gangi, Roldano Cattoni, Luisa Bentivogli, Matteo Negri, and Marco Turchi. 2019. MuST-C: a Multilingual Speech Translation Corpus. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (… [find](https://scholar.google.com/scholar?q=Mattia+A%2E+Di+Gangi%2C+Roldano+Cattoni%2C+Luisa+Bentivogli%2C+Matteo+Negri%2C+and+Marco+Turchi%2E+2019%2E+MuST%2DC%3A+a+Multilingual+Speech+Translation+Corpus%2E+In+Proceedings+of+the+2019+Conference+of+the+North+Americ) [our card](https://md.research.elamur.ai/free/papers/gangi-2019-must-c-multilingual-speech-translation/)
13. Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, et al. 2020. The second conversational intelligence challenge (convai2). In The NeurIPS’18 Competition: From Machine Learning to Intelligent Conversatio… [find](https://scholar.google.com/scholar?q=Emily+Dinan%2C+Varvara+Logacheva%2C+Valentin+Malykh%2C+Alexander+Miller%2C+Kurt+Shuster%2C+Jack+Urbanek%2C+Douwe+Kiela%2C+Arthur+Szlam%2C+Iulian+Serban%2C+Ryan+Lowe%2C+et+al%2E+2020%2E+The+second+conversational+intelligence+) [our card](https://md.research.elamur.ai/free/papers/dinan-2019-second-conversational-intelligence-challenge-convai2/)
14. Naman Goyal, Cynthia Gao, Vishrav Chaudhary, Peng-Jen Chen, Guillaume Wenzek, Da Ju, Sanjana Krishnan, Marc’Aurelio Ranzato, Francisco Guzmán, and Angela Fan. 2022. The flores-101 evaluation benchmark for low-resource and multilingual machine translation. Transactions of the Association for Computat… [find](https://scholar.google.com/scholar?q=Naman+Goyal%2C+Cynthia+Gao%2C+Vishrav+Chaudhary%2C+Peng%2DJen+Chen%2C+Guillaume+Wenzek%2C+Da+Ju%2C+Sanjana+Krishnan%2C+Marc%E2%80%99Aurelio+Ranzato%2C+Francisco+Guzm%C3%A1n%2C+and+Angela+Fan%2E+2022%2E+The+flores%2D101+evaluation+benchmark)
15. Alex Graves, Santiago Fernández, Faustino Gomez, and Jürgen Schmidhuber. 2006. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd international conference on Machine learning, pages 369–376. [find](https://scholar.google.com/scholar?q=Alex+Graves%2C+Santiago+Fern%C3%A1ndez%2C+Faustino+Gomez%2C+and+J%C3%BCrgen+Schmidhuber%2E+2006%2E+Connectionist+temporal+classification%3A+labelling+unsegmented+sequence+data+with+recurrent+neural+networks%2E+In+Proceedings)
16. Jonatas Grosman. 2021a. Fine-tuned XLSR-53 large model for speech recognition in Chinese. [https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn). [↗](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn)
17. Jonatas Grosman. 2021b. Fine-tuned XLSR-53 large model for speech recognition in English. [https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english). [↗](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english)
18. Jonatas Grosman. 2021c. Fine-tuned XLSR-53 large model for speech recognition in German. [https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-german](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-german). [↗](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-german)
19. Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio César Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, et al. 2023. Textbooks are all you need. arXiv preprint arXiv:2306.11644. [find](https://scholar.google.com/scholar?q=Suriya+Gunasekar%2C+Yi+Zhang%2C+Jyoti+Aneja%2C+Caio+C%C3%A9sar+Teodoro+Mendes%2C+Allie+Del+Giorno%2C+Sivakanth+Gopi%2C+Mojan+Javaheripi%2C+Piero+Kauffmann%2C+Gustavo+de+Rosa%2C+Olli+Saarikivi%2C+et+al%2E+2023%2E+Textbooks+are+all)
20. Injy Hamed, Pavel Denisov, Chia-Yu Li, Mohamed Elmahdy, Slim Abdennadher, and Ngoc Thang Vu. 2022. Investigations on speech recognition systems for low-resource dialectal arabic– english code-switching speech. Computer Speech & Language, 72:101278. [find](https://scholar.google.com/scholar?q=Injy+Hamed%2C+Pavel+Denisov%2C+Chia%2DYu+Li%2C+Mohamed+Elmahdy%2C+Slim+Abdennadher%2C+and+Ngoc+Thang+Vu%2E+2022%2E+Investigations+on+speech+recognition+systems+for+low%2Dresource+dialectal+arabic%E2%80%93+english+code%2Dswitchin)
21. Injy Hamed, Ngoc Thang Vu, and Slim Abdennadher. 2020. Arzen: A speech corpus for code-switched egyptian arabic-english. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 4237–4246. [find](https://scholar.google.com/scholar?q=Injy+Hamed%2C+Ngoc+Thang+Vu%2C+and+Slim+Abdennadher%2E+2020%2E+Arzen%3A+A+speech+corpus+for+code%2Dswitched+egyptian+arabic%2Denglish%2E+In+Proceedings+of+the+12th+Language+Resources+and+Evaluation+Conference%2C+pages+)
22. Trevor Hastie, Robert Tibshirani, and Jerome Friedman. 2009. The Elements of Statistical Learning – Data Mining, Inference, and Prediction. Springer, New York. [find](https://scholar.google.com/scholar?q=Trevor+Hastie%2C+Robert+Tibshirani%2C+and+Jerome+Friedman%2E+2009%2E+The+Elements+of+Statistical+Learning+%E2%80%93+Data+Mining%2C+Inference%2C+and+Prediction%2E+Springer%2C+New+York%2E)
23. Robert Jones, Firstname2 Lastname2, and Firstname3 Lastname3. 2022. An excellent paper introducing the ABC toolkit. In (Smith et al., 2022), pages 105–109. [find](https://scholar.google.com/scholar?q=Robert+Jones%2C+Firstname2+Lastname2%2C+and+Firstname3+Lastname3%2E+2022%2E+An+excellent+paper+introducing+the+ABC+toolkit%2E+In+%28Smith+et+al%2E%2C+2022%29%2C+pages+105%E2%80%93109%2E)
24. Shareef Babu Kalluri, Prachi Singh, Pratik Roy Chowdhuri, Apoorva Kulkarni, Shikha Baghel, Pradyoth Hegde, Swapnil Sontakke, SR Prasanna, Deepu Vijayasenan, Sriram Ganapathy, et al. 2024. The second displace challenge: Diarization of speaker and language in conversational environments. arXiv preprin… — [arXiv:2406.09494](https://arxiv.org/abs/2406.09494) [find](https://scholar.google.com/scholar?q=Shareef+Babu+Kalluri%2C+Prachi+Singh%2C+Pratik+Roy+Chowdhuri%2C+Apoorva+Kulkarni%2C+Shikha+Baghel%2C+Pradyoth+Hegde%2C+Swapnil+Sontakke%2C+SR+Prasanna%2C+Deepu+Vijayasenan%2C+Sriram+Ganapathy%2C+et+al%2E+2024%2E+The+second+d)
25. Ondřej Klejch, Electra Wallington, and Peter Bell. 2021. The cstr system for multilingual and code-switching asr challenges for low resource indian languages. In Interspeech 2021: The 22nd Annual Conference of the International Speech Communication Association, pages 2881–2885. International Speech… [find](https://scholar.google.com/scholar?q=Ond%C5%99ej+Klejch%2C+Electra+Wallington%2C+and+Peter+Bell%2E+2021%2E+The+cstr+system+for+multilingual+and+code%2Dswitching+asr+challenges+for+low+resource+indian+languages%2E+In+Interspeech+2021%3A+The+22nd+Annual+Conf)
26. Wessel Kraaij, Thomas Hain, Mike Lincoln, and Wilfried Post. 2005. The ami meeting corpus. In Proc. International Conference on Methods and Techniques in Behavioral Research, pages 1–4. [find](https://scholar.google.com/scholar?q=Wessel+Kraaij%2C+Thomas+Hain%2C+Mike+Lincoln%2C+and+Wilfried+Post%2E+2005%2E+The+ami+meeting+corpus%2E+In+Proc%2E+International+Conference+on+Methods+and+Techniques+in+Behavioral+Research%2C+pages+1%E2%80%934%2E)
27. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. Dailydialog: A manually labelled multi-turn dialogue dataset. arXiv preprint arXiv:1710.03957. [find](https://scholar.google.com/scholar?q=Yanran+Li%2C+Hui+Su%2C+Xiaoyu+Shen%2C+Wenjie+Li%2C+Ziqiang+Cao%2C+and+Shuzi+Niu%2E+2017%2E+Dailydialog%3A+A+manually+labelled+multi%2Dturn+dialogue+dataset%2E+arXiv+preprint+arXiv%3A1710%2E03957%2E) [our card](https://md.research.elamur.ai/free/papers/li-2017-dailydialog-manually-labelled-multi-turn/)
28. Zhaolin Li, Yining Liu, Danni Liu, Tuan Nam Nguyen, Enes Yavuz Ugan, Tu Anh Dinh, Carlos Mullov, Alexander Waibel, and Jan Niehues. 2025. Kit’s low-resource speech translation systems for iwslt2025: System enhancement with synthetic data and model regularization. arXiv preprint arXiv:2505.19679. [find](https://scholar.google.com/scholar?q=Zhaolin+Li%2C+Yining+Liu%2C+Danni+Liu%2C+Tuan+Nam+Nguyen%2C+Enes+Yavuz+Ugan%2C+Tu+Anh+Dinh%2C+Carlos+Mullov%2C+Alexander+Waibel%2C+and+Jan+Niehues%2E+2025%2E+Kit%E2%80%99s+low%2Dresource+speech+translation+systems+for+iwslt2025%3A+S)
29. Danni Liu, Thai Binh Nguyen, Sai Koneru, Enes Yavuz Ugan, Ngoc-Quan Pham, Tuan-Nam Nguyen, Tu Anh Dinh, Carlos Mullov, Alexander Waibel, and Jan Niehues. 2023. Kit’s multilingual speech translation system for iwslt 2023. arXiv preprint arXiv:2306.05320. [find](https://scholar.google.com/scholar?q=Danni+Liu%2C+Thai+Binh+Nguyen%2C+Sai+Koneru%2C+Enes+Yavuz+Ugan%2C+Ngoc%2DQuan+Pham%2C+Tuan%2DNam+Nguyen%2C+Tu+Anh+Dinh%2C+Carlos+Mullov%2C+Alexander+Waibel%2C+and+Jan+Niehues%2E+2023%2E+Kit%E2%80%99s+multilingual+speech+translation+sy)
30. Dau-Cheng Lyu, Tien Ping Tan, Engsiong Chng, and Haizhou Li. 2010. Seame: a mandarin-english code-switching speech corpus in southeast asia. Interspeech, pages 1986–1989. [find](https://scholar.google.com/scholar?q=Dau%2DCheng+Lyu%2C+Tien+Ping+Tan%2C+Engsiong+Chng%2C+and+Haizhou+Li%2E+2010%2E+Seame%3A+a+mandarin%2Denglish+code%2Dswitching+speech+corpus+in+southeast+asia%2E+Interspeech%2C+pages+1986%E2%80%931989%2E)
31. Roger K. Moore and Lucy Skidmore. 2019. On the use/misuse of the term ‘Phoneme’. In Proc. [find](https://scholar.google.com/scholar?q=Roger+K%2E+Moore+and+Lucy+Skidmore%2E+2019%2E+On+the+use%2Fmisuse+of+the+term+%E2%80%98Phoneme%E2%80%99%2E+In+Proc%2E)
32. INTERSPEECH 2019 – 20 th Annual Conference of the International Speech Communication Association, pages 2340–2344, Graz, Austria. [find](https://scholar.google.com/scholar?q=INTERSPEECH+2019+%E2%80%93+20+th+Annual+Conference+of+the+International+Speech+Communication+Association%2C+pages+2340%E2%80%932344%2C+Graz%2C+Austria%2E)
33. Bingshen Mu, Pengcheng Guo, Zhaokai Sun, Shuai Wang, Hexin Liu, Mingchen Shao, Lei Xie, Eng Siong Chng, Longshuai Xiao, Qiangze Feng, et al. 2025. Summary on the multilingual conversational speech language model challenge: Datasets, tasks, baselines, and methods. arXiv preprint arXiv:2509.13785. ozc… — [arXiv:2509.13785](https://arxiv.org/abs/2509.13785) [find](https://scholar.google.com/scholar?q=Bingshen+Mu%2C+Pengcheng+Guo%2C+Zhaokai+Sun%2C+Shuai+Wang%2C+Hexin+Liu%2C+Mingchen+Shao%2C+Lei+Xie%2C+Eng+Siong+Chng%2C+Longshuai+Xiao%2C+Qiangze+Feng%2C+et+al%2E+2025%2E+Summary+on+the+multilingual+conversational+speech+lan)
34. Lawrence R. Rabiner. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2):257–286. [find](https://scholar.google.com/scholar?q=Lawrence+R%2E+Rabiner%2E+1989%2E+A+tutorial+on+hidden+Markov+models+and+selected+applications+in+speech+recognition%2E+Proceedings+of+the+IEEE%2C+77%282%29%3A257%E2%80%93286%2E)
35. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning, pages 28492–28518. PMLR. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jong+Wook+Kim%2C+Tao+Xu%2C+Greg+Brockman%2C+Christine+McLeavey%2C+and+Ilya+Sutskever%2E+2023%2E+Robust+speech+recognition+via+large%2Dscale+weak+supervision%2E+In+International+Conference+on+Machine+Lea) [our card](https://md.research.elamur.ai/free/papers/radford-2022-robust-speech-recognition-large-scale/)
36. Nathaniel Romney Robinson, Niyati Bafna, Xiluo He, Tom Lupicki, Lavanya Shankar, Cihan Xiao, Qi Sun, Kenton Murray, and David Yarowsky. 2025. Jhu iwslt 2025 low-resource system description. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 315–323… [find](https://scholar.google.com/scholar?q=Nathaniel+Romney+Robinson%2C+Niyati+Bafna%2C+Xiluo+He%2C+Tom+Lupicki%2C+Lavanya+Shankar%2C+Cihan+Xiao%2C+Qi+Sun%2C+Kenton+Murray%2C+and+David+Yarowsky%2E+2025%2E+Jhu+iwslt+2025+low%2Dresource+system+description%2E+In+Proceed)
37. Jiatong Shi, Shih-Heng Wang, William Chen, Martijn Bartelds, Vanya Bannihatti Kumar, Jinchuan Tian, Xuankai Chang, Dan Jurafsky, Karen Livescu, Hung-yi Lee, et al. 2024. Ml-superb 2.0: Benchmarking multilingual speech models across modeling constraints, languages, and datasets. arXiv preprint arXiv:… — [arXiv:2406.08641](https://arxiv.org/abs/2406.08641) [find](https://scholar.google.com/scholar?q=Jiatong+Shi%2C+Shih%2DHeng+Wang%2C+William+Chen%2C+Martijn+Bartelds%2C+Vanya+Bannihatti+Kumar%2C+Jinchuan+Tian%2C+Xuankai+Chang%2C+Dan+Jurafsky%2C+Karen+Livescu%2C+Hung%2Dyi+Lee%2C+et+al%2E+2024%2E+Ml%2Dsuperb+2%2E0%3A+Benchmarking+mu)
38. Supriti Sinhamahapatra and Jan Niehues. 2025. Do slides help? multi-modal context for automatic transcription of conference talks. [find](https://scholar.google.com/scholar?q=Supriti+Sinhamahapatra+and+Jan+Niehues%2E+2025%2E+Do+slides+help%3F+multi%2Dmodal+context+for+automatic+transcription+of+conference+talks%2E)
39. Jane Smith, Firstname2 Lastname2, and Firstname3 Lastname3. 2022. A really good paper about Dynamic Time Warping. In Proc. [find](https://scholar.google.com/scholar?q=Jane+Smith%2C+Firstname2+Lastname2%2C+and+Firstname3+Lastname3%2E+2022%2E+A+really+good+paper+about+Dynamic+Time+Warping%2E+In+Proc%2E)
40. INTER-SPEECH 2022 – 23 rd Annual Conference of the International Speech Communication Association, pages 100–104, Incheon, Korea. [find](https://scholar.google.com/scholar?q=INTER%2DSPEECH+2022+%E2%80%93+23+rd+Annual+Conference+of+the+International+Speech+Communication+Association%2C+pages+100%E2%80%93104%2C+Incheon%2C+Korea%2E)
41. Label Studio. 2023. Label studio: Open source data labeling platform. [find](https://scholar.google.com/scholar?q=Label+Studio%2E+2023%2E+Label+studio%3A+Open+source+data+labeling+platform%2E)
42. Changli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, and Chao Zhang. 2023. Salmonn: Towards generic hearing abilities for large language models. arXiv preprint arXiv:2310.13289. [find](https://scholar.google.com/scholar?q=Changli+Tang%2C+Wenyi+Yu%2C+Guangzhi+Sun%2C+Xianzhao+Chen%2C+Tian+Tan%2C+Wei+Li%2C+Lu+Lu%2C+Zejun+Ma%2C+and+Chao+Zhang%2E+2023%2E+Salmonn%3A+Towards+generic+hearing+abilities+for+large+language+models%2E+arXiv+preprint+arXiv) [our card](https://md.research.elamur.ai/free/papers/tang-2023-salmonn-towards-generic-hearing-abilities/)
43. Ioannis Tsiamas, Gerard I. Gállego, José A. R. Fonollosa, and Marta R. Costa-jussà. 2022. [find](https://scholar.google.com/scholar?q=Ioannis+Tsiamas%2C+Gerard+I%2E+G%C3%A1llego%2C+Jos%C3%A9+A%2E+R%2E+Fonollosa%2C+and+Marta+R%2E+Costa%2Djuss%C3%A0%2E+2022%2E)
44. Shas: Approaching optimal segmentation for end-to-end speech translation. [find](https://scholar.google.com/scholar?q=Shas%3A+Approaching+optimal+segmentation+for+end%2Dto%2Dend+speech+translation%2E)
45. Enes Yavuz Ugan, Christian Huber, Juan Hussain, and Alexander Waibel. 2022. Language-agnostic code-switching in sequence-to-sequence speech recognition. arXiv preprint arXiv:2210.08992. — [arXiv:2210.08992](https://arxiv.org/abs/2210.08992) [find](https://scholar.google.com/scholar?q=Enes+Yavuz+Ugan%2C+Christian+Huber%2C+Juan+Hussain%2C+and+Alexander+Waibel%2E+2022%2E+Language%2Dagnostic+code%2Dswitching+in+sequence%2Dto%2Dsequence+speech+recognition%2E+arXiv+preprint+arXiv%3A2210%2E08992%2E+%E2%80%94+%5BarXiv%3A2210%2E)
46. Enes Yavuz Ugan, Ngoc-Quan Pham, Leonard Bärmann, and Alex Waibel. 2025a. Pier: A novel metric for evaluating what matters in code-switching. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE. [find](https://scholar.google.com/scholar?q=Enes+Yavuz+Ugan%2C+Ngoc%2DQuan+Pham%2C+Leonard+B%C3%A4rmann%2C+and+Alex+Waibel%2E+2025a%2E+Pier%3A+A+novel+metric+for+evaluating+what+matters+in+code%2Dswitching%2E+In+ICASSP+2025%2D2025+IEEE+International+Conference+on+Acous)
47. Enes Yavuz Ugan, Ngoc-Quan Pham, and Alexander Waibel. 2024. DECM: Evaluating bilingual ASR performance on a code-switching/mixing benchmark. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4468–4475,… [find](https://scholar.google.com/scholar?q=Enes+Yavuz+Ugan%2C+Ngoc%2DQuan+Pham%2C+and+Alexander+Waibel%2E+2024%2E+DECM%3A+Evaluating+bilingual+ASR+performance+on+a+code%2Dswitching%2Fmixing+benchmark%2E+In+Proceedings+of+the+2024+Joint+International+Conference+)
48. Enes Yavuz Ugan, Ngoc-Quan Pham, and Alexander Waibel. 2025b. Weight factorization and centralization for continual learning in speech recognition. arXiv preprint arXiv:2506.16574. — [arXiv:2506.16574](https://arxiv.org/abs/2506.16574) [find](https://scholar.google.com/scholar?q=Enes+Yavuz+Ugan%2C+Ngoc%2DQuan+Pham%2C+and+Alexander+Waibel%2E+2025b%2E+Weight+factorization+and+centralization+for+continual+learning+in+speech+recognition%2E+arXiv+preprint+arXiv%3A2506%2E16574%2E+%E2%80%94+%5BarXiv%3A2506%2E16574)
49. Maarten Van Segbroeck, Ahmed Zaid, Ksenia Kutsenko, Cirenia Huerta, Tinh Nguyen, Xuewen Luo, Björn Hoffmeister, Jan Trmal, Maurizio Omologo, and Roland Maas. 2019. Dipco–dinner party corpus. arXiv preprint arXiv:1909.13447. — [arXiv:1909.13447](https://arxiv.org/abs/1909.13447) [find](https://scholar.google.com/scholar?q=Maarten+Van+Segbroeck%2C+Ahmed+Zaid%2C+Ksenia+Kutsenko%2C+Cirenia+Huerta%2C+Tinh+Nguyen%2C+Xuewen+Luo%2C+Bj%C3%B6rn+Hoffmeister%2C+Jan+Trmal%2C+Maurizio+Omologo%2C+and+Roland+Maas%2E+2019%2E+Dipco%E2%80%93dinner+party+corpus%2E+arXiv+pre)
50. Patrick von Platen. 2021. Fine-tuned XLSR-53 large model for speech recognition in vietnamese. [https://huggingface.co/not-tanh/wav2vec2-large-xlsr-53-vietnamese](https://huggingface.co/not-tanh/wav2vec2-large-xlsr-53-vietnamese). [↗](https://huggingface.co/not-tanh/wav2vec2-large-xlsr-53-vietnamese)
51. Changhan Wang, Anne Wu, and Juan Pino. 2020. Covost 2: A massively multilingual speech-to-text translation corpus. [find](https://scholar.google.com/scholar?q=Changhan+Wang%2C+Anne+Wu%2C+and+Juan+Pino%2E+2020%2E+Covost+2%3A+A+massively+multilingual+speech%2Dto%2Dtext+translation+corpus%2E)
52. Hao Wang, Shuhei Kurita, Shuichiro Shimizu, and Daisuke Kawahara. 2024. Slideavsr: A dataset of paper explanation videos for audio-visual speech recognition. arXiv preprint arXiv:2401.09759. [find](https://scholar.google.com/scholar?q=Hao+Wang%2C+Shuhei+Kurita%2C+Shuichiro+Shimizu%2C+and+Daisuke+Kawahara%2E+2024%2E+Slideavsr%3A+A+dataset+of+paper+explanation+videos+for+audio%2Dvisual+speech+recognition%2E+arXiv+preprint+arXiv%3A2401%2E09759%2E)
53. Peng Xie, Xingyuan Liu, Tsz Wai Chan, Yequan Bie, Yangqiu Song, Yang Wang, Hao Chen, and Kani Chen. 2025. Switchlingua: The first large-scale multilingual and multi-ethnic code-switching dataset. arXiv preprint arXiv:2506.00087. — [arXiv:2506.00087](https://arxiv.org/abs/2506.00087) [find](https://scholar.google.com/scholar?q=Peng+Xie%2C+Xingyuan+Liu%2C+Tsz+Wai+Chan%2C+Yequan+Bie%2C+Yangqiu+Song%2C+Yang+Wang%2C+Hao+Chen%2C+and+Kani+Chen%2E+2025%2E+Switchlingua%3A+The+first+large%2Dscale+multilingual+and+multi%2Dethnic+code%2Dswitching+dataset%2E+arXi)
54. Guanrou Yang, Ziyang Ma, Fan Yu, Zhifu Gao, Shiliang Zhang, and Xie Chen. 2024. Mala-asr: Multimedia-assisted llm-based asr. arXiv preprint arXiv:2406.05839. — [arXiv:2406.05839](https://arxiv.org/abs/2406.05839) [find](https://scholar.google.com/scholar?q=Guanrou+Yang%2C+Ziyang+Ma%2C+Fan+Yu%2C+Zhifu+Gao%2C+Shiliang+Zhang%2C+and+Xie+Chen%2E+2024%2E+Mala%2Dasr%3A+Multimedia%2Dassisted+llm%2Dbased+asr%2E+arXiv+preprint+arXiv%3A2406%2E05839%2E+%E2%80%94+%5BarXiv%3A2406%2E05839%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs)
55. Qiming Zhang, Jing Zhang, Yufei Xu, and Dacheng Tao. 2024. Vision transformer with quadrangle attention. IEEE Transactions on Pattern Analysis and Machine Intelligence. [find](https://scholar.google.com/scholar?q=Qiming+Zhang%2C+Jing+Zhang%2C+Yufei+Xu%2C+and+Dacheng+Tao%2E+2024%2E+Vision+transformer+with+quadrangle+attention%2E+IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence%2E)
56. Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2019. Dialogpt: Large-scale generative pre-training for conversational response generation. CoRR, abs/1911.00536. [find](https://scholar.google.com/scholar?q=Yizhe+Zhang%2C+Siqi+Sun%2C+Michel+Galley%2C+Yen%2DChun+Chen%2C+Chris+Brockett%2C+Xiang+Gao%2C+Jianfeng+Gao%2C+Jingjing+Liu%2C+and+Bill+Dolan%2E+2019%2E+Dialogpt%3A+Large%2Dscale+generative+pre%2Dtraining+for+conversational+respo) [our card](https://md.research.elamur.ai/free/papers/zhang-2019-dialogpt-large-scale-generative-pre/)