---
title: "Team QUESPA System Submission for the IWSLT — Ortega 2026"
description: "This paper describes the QUESPA team's fourth consecutive entry in the IWSLT low-resource speech translation track, which in 2026 covered Quechua→Spanish…"
authors: ["John E. Ortega", "Rodolfo Joel Zevallos", "Fabrício Carraro", "Stephanny Gabriela Sánchez Bautista", "Chad Howe"]
year: 2026
venue: "Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)"
source: "https://aclanthology.org/2026.iwslt-1.5/"
doi: "10.18653/v1/2026.iwslt-1.5"
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/papers/ortega-2026-team-quespa-system-submission-iwslt/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/ortega-2026-team-quespa-system-submission-iwslt/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/4/) / Team QUESPA System Submission for the IWSLT 2026 Dialectal and Low-resource Speech Translation Task

# Team QUESPA System Submission for the IWSLT 2026 Dialectal and Low-resource Speech Translation Task

**Authors:** [John E. Ortega](https://md.research.elamur.ai/free/authors/john-e-ortega/), [Rodolfo Joel Zevallos](https://md.research.elamur.ai/free/authors/rodolfo-joel-zevallos/), [Fabrício Carraro](https://md.research.elamur.ai/free/authors/fabricio-carraro/), Stephanny Gabriela Sánchez Bautista, Chad Howe · **Year:** 2026 · **Venue:** Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.iwslt-1.5/) · [PDF](https://aclanthology.org/2026.iwslt-1.5.pdf) · [DOI 10.18653/v1/2026.iwslt-1.5](https://doi.org/10.18653/v1/2026.iwslt-1.5) · [OpenAlex](https://openalex.org/W7166800727)

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

## Summary

This paper describes the QUESPA team's fourth consecutive entry in the IWSLT low-resource speech translation track, which in 2026 covered Quechua→Spanish in an unconstrained-only setting. Quechua is agglutinative, has millions of speakers, and has very little paired speech-translation data. The team submitted three systems. Two are cascades, using Mamba ASR or Whisper Large V3 followed by a fine-tuned NLLB MT model. The third is an end-to-end SpeechT5 model. All three newly pass the audio through SIDON speech enhancement first. The SpeechT5 system was also trained with data augmentation and an added Quechua Collao (quz) corpus. That system performed best, scoring 27.2 BLEU and slightly improving on the team's 2025 record of 26.7. SIDON added modest BLEU gains to the cascades, but its effect on CHRF was inconsistent. The authors also ran a case study comparing prompting of commercial LLMs against the fine-tuned NLLB model, and none of the LLMs matched it. The results suggest that fine-tuned task-specific models still beat general LLM prompting for this Indigenous language pair.

## Key points

- **Task data:**
  - about 1h40m of Quechua–Spanish speech translation data;
  - roughly 48h of transcribed ASR audio from the Siminchik radio corpus;
  - an MT text corpus;
  - two new official additions: post-edited machine-translated Huqariq text and a Quechua Collao (quz) corpus, both hosted on the IWSLT GitHub.
- **BLEU on the official test set:**
  - primary (Mamba ASR + SIDON + NLLB): 15.0, up from 14.8 in 2025;
  - contrastive 1 (Whisper Large V3 + SIDON + NLLB): 15.4, up from 15.0;
  - contrastive 2 (SpeechT5): 27.2, up from 26.7.
- **Contrastive 2 training data:** 48h of original audio, plus 48h of nlpaug-generated synthetic audio (noise, distortion, duplication), plus about 15h of quz speech.
- **MT case study:** prompted LLMs (GPT-5.4, Gemini 3, Claude Haiku/Sonnet, DeepSeek-V3.1/3.2, Qwen 3.6 Plus) all scored well below the 2025 fine-tuned NLLB-200 1.3B baseline of 19.5 BLEU / 23.5 CHRF.
- **Future work:** the authors plan more human annotation and want to test Omnilingual MT in later campaigns.

*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/) · [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/)

Topics: [Machine translation](https://md.research.elamur.ai/free/topics/machine-translation/)

## Cite

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

```bibtex
@inproceedings{ortega2026team,
  title = {{Team QUESPA System Submission for the IWSLT 2026 Dialectal and Low-resource Speech Translation Task}},
  author = {Ortega, John E. and Zevallos, Rodolfo Joel and Carraro, Fabrício and Bautista, Stephanny Gabriela Sánchez and Howe, Chad},
  booktitle = {Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.iwslt-1.5},
  url = {https://doi.org/10.18653/v1/2026.iwslt-1.5}
}
```

- [← previous Teaching linguistic prompt control for LLM based translation: A classroom approach to developing critical and responsible AI literacy](https://md.research.elamur.ai/free/papers/menzel-2026-teaching-linguistic-prompt-control-llm/)
- [next → TempPerturb-Eval: On the Joint Effects of Internal Temperature and External Perturbations in RAG Robustness](https://md.research.elamur.ai/free/papers/zhou-2026-tempperturb-eval-joint-effects-internal/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/4/)

## References

46 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Milind Agarwal, Sweta Agrawal, Antonios Anastasopoulos, Ondřej Bojar, Claudia Borg, Marine Carpuat, Roldano Cattoni, Mauro Cettolo, Mingda Chen, William Chen, Khalid Choukri, Alexandra Chronopoulou, Anna Currey, Thierry Declerck, Qianqian Dong, Yannick Estève, Kevin Duh, Marcello Federico, Souhir G… [find](https://scholar.google.com/scholar?q=Milind+Agarwal%2C+Sweta+Agrawal%2C+Antonios+Anastasopoulos%2C+Ondr%CC%8Cej+Bojar%2C+Claudia+Borg%2C+Marine+Carpuat%2C+Roldano+Cattoni%2C+Mauro+Cettolo%2C+Mingda+Chen%2C+William+Chen%2C+Khalid+Choukri%2C+Alexandra+Chronopoulou%2C+) [our card](https://md.research.elamur.ai/free/papers/agarwal-2023-findings-iwslt-2023-evaluation-campaign/)
2. Conclusion and Future Work Our submission to the IWSLT 2026 () evaluation campaign for low-resource and dialect speech translation includes novelties based on the most state-of-the-art techniques for ASR and ST. The addition [https://github.com/makcedward/nlpaug](https://github.com/makcedward/nlpaug) [↗](https://github.com/makcedward/nlpaug)
3. Victor Agostinelli, Tanel Alumäe, Antonios Anastasopoulos, Luisa Bentivogli, Ondřej Bojar, Claudia Borg, Fethi Bougares, Roldano Cattoni, Mauro Cettolo, Lizhong Chen, et al. 2025. Findings of the iwslt 2025 evaluation campaign. In Proceedings of the 22nd International Conference on Spoken Language… [find](https://scholar.google.com/scholar?q=Victor+Agostinelli%2C+Tanel+Alum%C3%A4e%2C+Antonios+Anastasopoulos%2C+Luisa+Bentivogli%2C+Ondr%CC%8Cej+Bojar%2C+Claudia+Borg%2C+Fethi+Bougares%2C+Roldano+Cattoni%2C+Mauro+Cettolo%2C+Lizhong+Chen%2C+et+al%2E+2025%2E+Findings+of+the+iws)
4. Bruno Barbaran and Wilfredo Ticona. 2024. Implementation of a natural language processing model for spanish-quechua machine translation. In Proceedings of the Computational Methods in Systems and Software, pages 464–476. Springer. [find](https://scholar.google.com/scholar?q=Bruno+Barbaran+and+Wilfredo+Ticona%2E+2024%2E+Implementation+of+a+natural+language+processing+model+for+spanish%2Dquechua+machine+translation%2E+In+Proceedings+of+the+Computational+Methods+in+Systems+and+Soft)
5. Ronald Cardenas, Rodolfo Zevallos, Reynaldo Baquer-izo, and Luis Camacho. 2018. Siminchik: A speech corpus for preservation of southern quechua. ISI-NLP 2, page 21. [find](https://scholar.google.com/scholar?q=Ronald+Cardenas%2C+Rodolfo+Zevallos%2C+Reynaldo+Baquer%2Dizo%2C+and+Luis+Camacho%2E+2018%2E+Siminchik%3A+A+speech+corpus+for+preservation+of+southern+quechua%2E+ISI%2DNLP+2%2C+page+21%2E)
6. Ibrahim Said Ahmad, Antonios Anastasopoulos, Ondřej Bojar, Claudia Borg, Marine Carpuat, Roldano Cattoni, Mauro Cettolo, William Chen, Qianqian Dong, Marcello Federico, Barry Haddow, Dávid Javorský, Mateusz Krubiński, Tsz Kin Lam, Xutai Ma, Prashant Mathur, Evgeny Matusov, Chandresh Maurya, John M… [find](https://scholar.google.com/scholar?q=Ibrahim+Said+Ahmad%2C+Antonios+Anastasopoulos%2C+Ondr%CC%8Cej+Bojar%2C+Claudia+Borg%2C+Marine+Carpuat%2C+Roldano+Cattoni%2C+Mauro+Cettolo%2C+William+Chen%2C+Qianqian+Dong%2C+Marcello+Federico%2C+Barry+Haddow%2C+D%C3%A1vid+Javorsk%C3%BD%2C+)
7. FINDINGS OF THE IWSLT 2024 EVALUATION CAMPAIGN. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 1–11, Bangkok, Thailand (in-person and online). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=FINDINGS+OF+THE+IWSLT+2024+EVALUATION+CAMPAIGN%2E+In+Proceedings+of+the+21st+International+Conference+on+Spoken+Language+Translation+%28IWSLT+2024%29%2C+pages+1%E2%80%9311%2C+Bangkok%2C+Thailand+%28in%2Dperson+and+online%29%2E+A)
8. Rodrigo M. Carrillo-Larco, Jesús Lovón-Melgarejo, Manuel Castillo-Cara, and Gusseppe Bravo-Rocca. 2026. PeruMedQA: Benchmarking Large Language Models (LLMs) on Peruvian Medical Exams—Dataset Construction and Evaluation. Medical Science Educator. [find](https://scholar.google.com/scholar?q=Rodrigo+M%2E+Carrillo%2DLarco%2C+Jes%C3%BAs+Lov%C3%B3n%2DMelgarejo%2C+Manuel+Castillo%2DCara%2C+and+Gusseppe+Bravo%2DRocca%2E+2026%2E+PeruMedQA%3A+Benchmarking+Large+Language+Models+%28LLMs%29+on+Peruvian+Medical+Exams%E2%80%94Dataset+Construct)
9. Chih-Chen Chen, William Chen, Rodolfo Zevallos, and John Ortega. 2023a. Evaluating self-supervised speech representations for indigenous american languages. arXiv preprint arXiv:2310.03639. [find](https://scholar.google.com/scholar?q=Chih%2DChen+Chen%2C+William+Chen%2C+Rodolfo+Zevallos%2C+and+John+Ortega%2E+2023a%2E+Evaluating+self%2Dsupervised+speech+representations+for+indigenous+american+languages%2E+arXiv+preprint+arXiv%3A2310%2E03639%2E)
10. William Chen, Brian Yan, Jiatong Shi, Yifan Peng, Soumi Maiti, and Shinji Watanabe. 2023b. Improving massively multilingual asr with auxiliary CTC objectives. arXiv preprint arXiv:2302.12829. — [arXiv:2302.12829](https://arxiv.org/abs/2302.12829) [find](https://scholar.google.com/scholar?q=William+Chen%2C+Brian+Yan%2C+Jiatong+Shi%2C+Yifan+Peng%2C+Soumi+Maiti%2C+and+Shinji+Watanabe%2E+2023b%2E+Improving+massively+multilingual+asr+with+auxiliary+CTC+objectives%2E+arXiv+preprint+arXiv%3A2302%2E12829%2E+%E2%80%94+%5BarXiv)
11. Alexis Conneau, Min Ma, Simran Khanuja, Yu Zhang, Vera Axelrod, Siddharth Dalmia, Jason Riesa, Clara Rivera, and Ankur Bapna. 2023. Fleurs: Few-shot learning evaluation of universal representations of speech. In 2022 IEEE Spoken Language Technology Workshop (SLT), pages 798–805. [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Min+Ma%2C+Simran+Khanuja%2C+Yu+Zhang%2C+Vera+Axelrod%2C+Siddharth+Dalmia%2C+Jason+Riesa%2C+Clara+Rivera%2C+and+Ankur+Bapna%2E+2023%2E+Fleurs%3A+Few%2Dshot+learning+evaluation+of+universal+representations+of) [our card](https://md.research.elamur.ai/free/papers/conneau-2022-fleurs-few-shot-learning-evaluation/)
12. Nouman Ahmed, Natalia Flechas Manrique, and An-tonije Petrović. 2023. Enhancing spanish-quechua machine translation with pre-trained models and diverse data sources: Lct-ehu at americasnlp shared task. In Proceedings of the Workshop on Natural Language Processing for Indigenous Languages of the Ame… [find](https://scholar.google.com/scholar?q=Nouman+Ahmed%2C+Natalia+Flechas+Manrique%2C+and+An%2Dtonije+Petrovic%CC%81%2E+2023%2E+Enhancing+spanish%2Dquechua+machine+translation+with+pre%2Dtrained+models+and+diverse+data+sources%3A+Lct%2Dehu+at+americasnlp+shared+tas)
13. Ona de Giberto, Robert Pugh, Ali Marashian, Raúl Vázquezo Abteen Ebrahimi, Pavel Denisov, Enora Rice, Edward Gow-Smithγ, Juan C Prietoβ, Melissa Roblesβ, Rubén Manriqueβ, et al. 2025. Findings of the americasnlp 2025 shared tasks on machine translation, creation of educational material, and translat… [find](https://scholar.google.com/scholar?q=Ona+de+Giberto%2C+Robert+Pugh%2C+Ali+Marashian%2C+Ra%C3%BAl+V%C3%A1zquezo+Abteen+Ebrahimi%2C+Pavel+Denisov%2C+Enora+Rice%2C+Edward+Gow%2DSmith%CE%B3%2C+Juan+C+Prieto%CE%B2%2C+Melissa+Robles%CE%B2%2C+Rub%C3%A9n+Manrique%CE%B2%2C+et+al%2E+2025%2E+Findings+of+the+)
14. Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, and Furu Wei. 2022. SpeechT5: Unified-modal encoder-decoder pre-training for spoken language processing. In Proceedings of the 60th Annual Meeting of the Association f… [find](https://scholar.google.com/scholar?q=Junyi+Ao%2C+Rui+Wang%2C+Long+Zhou%2C+Chengyi+Wang%2C+Shuo+Ren%2C+Yu+Wu%2C+Shujie+Liu%2C+Tom+Ko%2C+Qing+Li%2C+Yu+Zhang%2C+Zhihua+Wei%2C+Yao+Qian%2C+Jinyu+Li%2C+and+Furu+Wei%2E+2022%2E+SpeechT5%3A+Unified%2Dmodal+encoder%2Ddecoder+pre%2Dtra)
15. John E. Ortega, Rodolfo Zevallos, and William Chen. 2023. QUESPA submission for the IWSLT 2023 dialect and low-resource speech translation tasks. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 261–268, Toronto, Canada (in-person and online). As… [find](https://scholar.google.com/scholar?q=John+E%2E+Ortega%2C+Rodolfo+Zevallos%2C+and+William+Chen%2E+2023%2E+QUESPA+submission+for+the+IWSLT+2023+dialect+and+low%2Dresource+speech+translation+tasks%2E+In+Proceedings+of+the+20th+International+Conference+on)
16. Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, et al. 2021. Speecht5: Unified-modal encoder-decoder pre-training for spoken language processing. arXiv preprint arXiv:2110.07205. [find](https://scholar.google.com/scholar?q=Junyi+Ao%2C+Rui+Wang%2C+Long+Zhou%2C+Chengyi+Wang%2C+Shuo+Ren%2C+Yu+Wu%2C+Shujie+Liu%2C+Tom+Ko%2C+Qing+Li%2C+Yu+Zhang%2C+et+al%2E+2021%2E+Speecht5%3A+Unified%2Dmodal+encoder%2Ddecoder+pre%2Dtraining+for+spoken+language+processing%2E+a)
17. Abteen Ebrahimi, Manuel Mager, Shruti Rijhwani, Enora Rice, Arturo Oncevay, Claudia Baltazar, María Cortés, Cynthia Montaño, John E Ortega, Rolando Coto-Solano, et al. 2023. Findings of the americasnlp 2023 shared task on machine translation into indigenous languages. In Proceedings of the Workshop… [find](https://scholar.google.com/scholar?q=Abteen+Ebrahimi%2C+Manuel+Mager%2C+Shruti+Rijhwani%2C+Enora+Rice%2C+Arturo+Oncevay%2C+Claudia+Baltazar%2C+Mar%C3%ADa+Cort%C3%A9s%2C+Cynthia+Monta%C3%B1o%2C+John+E+Ortega%2C+Rolando+Coto%2DSolano%2C+et+al%2E+2023%2E+Findings+of+the+americasnl)
18. Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, et al. 2021. Xls-r: Self-supervised cross-lingual speech representation learning at scale. arXiv preprint arXiv:2111.09296. [find](https://scholar.google.com/scholar?q=Arun+Babu%2C+Changhan+Wang%2C+Andros+Tjandra%2C+Kushal+Lakhotia%2C+Qiantong+Xu%2C+Naman+Goyal%2C+Kritika+Singh%2C+Patrick+von+Platen%2C+Yatharth+Saraf%2C+Juan+Pino%2C+et+al%2E+2021%2E+Xls%2Dr%3A+Self%2Dsupervised+cross%2Dlingual+spe) [our card](https://md.research.elamur.ai/free/papers/babu-2021-xls-r-self-supervised-cross/)
19. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609. [find](https://scholar.google.com/scholar?q=Jinze+Bai%2C+Shuai+Bai%2C+Yunfei+Chu%2C+Zeyu+Cui%2C+Kai+Dang%2C+Xiaodong+Deng%2C+Yang+Fan%2C+Wenbin+Ge%2C+Yu+Han%2C+Fei+Huang%2C+et+al%2E+2023%2E+Qwen+technical+report%2E+arXiv+preprint+arXiv%3A2309%2E16609%2E) [our card](https://md.research.elamur.ai/free/papers/bai-2023-qwen-technical-report/)
20. Abteen Ebrahimi, Manuel Mager, Adam Wiemerslage, Pavel Denisov, Arturo Oncevay, Danni Liu, Sai Koneru, Enes Yavuz Ugan, Zhaolin Li, Jan Niehues, Monica Romero, Ivan G Torre, Tanel Alumäe, Jiaming Kong, Sergey Polezhaev, Yury Belousov, Wei-Rui Chen, Peter Sullivan, Ife Adebara, Bashar Talafha, Alcide… [find](https://scholar.google.com/scholar?q=Abteen+Ebrahimi%2C+Manuel+Mager%2C+Adam+Wiemerslage%2C+Pavel+Denisov%2C+Arturo+Oncevay%2C+Danni+Liu%2C+Sai+Koneru%2C+Enes+Yavuz+Ugan%2C+Zhaolin+Li%2C+Jan+Niehues%2C+Monica+Romero%2C+Ivan+G+Torre%2C+Tanel+Alum%C3%A4e%2C+Jiaming+Kong)
21. Wataru Nakata, Yuki Saito, Yota Ueda, and Hiroshi Saruwatari. 2025. Sidon: Fast and robust open-source multilingual speech restoration for large-scale dataset cleansing. arXiv preprint arXiv:2509.17052. [find](https://scholar.google.com/scholar?q=Wataru+Nakata%2C+Yuki+Saito%2C+Yota+Ueda%2C+and+Hiroshi+Saruwatari%2E+2025%2E+Sidon%3A+Fast+and+robust+open%2Dsource+multilingual+speech+restoration+for+large%2Dscale+dataset+cleansing%2E+arXiv+preprint+arXiv%3A2509%2E1705)
22. NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia-Gonzalez, Prangthip Hansanti, John Hof… [find](https://scholar.google.com/scholar?q=NLLB+Team%2C+Marta+R%2E+Costa%2Djuss%C3%A0%2C+James+Cross%2C+Onur+%C3%87elebi%2C+Maha+Elbayad%2C+Kenneth+Heafield%2C+Kevin+Heffernan%2C+Elahe+Kalbassi%2C+Janice+Lam%2C+Daniel+Licht%2C+Jean+Maillard%2C+Anna+Sun%2C+Skyler+Wang%2C+Guillaume+We)
23. Edward Gow-Smith, Alexandre Berard, Marcely Zanon Boito, and Ioan Calapodescu. 2023. NAVER LABS Europe‘s multilingual speech translation systems for the IWSLT 2023 low-resource track. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 144–158, Toro… [find](https://scholar.google.com/scholar?q=Edward+Gow%2DSmith%2C+Alexandre+Berard%2C+Marcely+Zanon+Boito%2C+and+Ioan+Calapodescu%2E+2023%2E+NAVER+LABS+Europe%E2%80%98s+multilingual+speech+translation+systems+for+the+IWSLT+2023+low%2Dresource+track%2E+In+Proceedings+o)
24. John E Ortega, Richard Castro Mamani, and Kyunghyun Cho. 2020. Neural machine translation with a polysynthetic low resource language. Machine Translation, 34(4):325–346. [find](https://scholar.google.com/scholar?q=John+E+Ortega%2C+Richard+Castro+Mamani%2C+and+Kyunghyun+Cho%2E+2020%2E+Neural+machine+translation+with+a+polysynthetic+low+resource+language%2E+Machine+Translation%2C+34%284%29%3A325%E2%80%93346%2E)
25. Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, and Ruoming Pang. 2020. Conformer: Convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100. [find](https://scholar.google.com/scholar?q=Anmol+Gulati%2C+James+Qin%2C+Chung%2DCheng+Chiu%2C+Niki+Parmar%2C+Yu+Zhang%2C+Jiahui+Yu%2C+Wei+Han%2C+Shibo+Wang%2C+Zhengdong+Zhang%2C+Yonghui+Wu%2C+and+Ruoming+Pang%2E+2020%2E+Conformer%3A+Convolution%2Daugmented+transformer+for+) [our card](https://md.research.elamur.ai/free/papers/gulati-2020-conformer-convolution-augmented-transformer-speech/)
26. John E Ortega and Krishnan Pillaipakkamnatt. 2018. Using morphemes from agglutinative languages like quechua and finnish to aid in low-resource translation. Technologies for MT of Low Resource Languages (LoResMT 2018), page 1. [find](https://scholar.google.com/scholar?q=John+E+Ortega+and+Krishnan+Pillaipakkamnatt%2E+2018%2E+Using+morphemes+from+agglutinative+languages+like+quechua+and+finnish+to+aid+in+low%2Dresource+translation%2E+Technologies+for+MT+of+Low+Resource+Languag)
27. Xilin Jiang, Yinghao Aaron Li, Adrian Nicolas Florea, Cong Han, and Nima Mesgarani. 2024. Speech slytherin: Examining the performance and efficiency of mamba for speech separation, recognition, and synthesis. arXiv preprint arXiv:2407.09732. — [arXiv:2407.09732](https://arxiv.org/abs/2407.09732) [find](https://scholar.google.com/scholar?q=Xilin+Jiang%2C+Yinghao+Aaron+Li%2C+Adrian+Nicolas+Florea%2C+Cong+Han%2C+and+Nima+Mesgarani%2E+2024%2E+Speech+slytherin%3A+Examining+the+performance+and+efficiency+of+mamba+for+speech+separation%2C+recognition%2C+and+sy)
28. John E Ortega, Rodolfo Joel Zevallos, William Chen, and Idris Abdulmumin. 2025. Quespa submission for the iwslt 2025 dialectal and low-resource speech translation task. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 260–268. [find](https://scholar.google.com/scholar?q=John+E+Ortega%2C+Rodolfo+Joel+Zevallos%2C+William+Chen%2C+and+Idris+Abdulmumin%2E+2025%2E+Quespa+submission+for+the+iwslt+2025+dialectal+and+low%2Dresource+speech+translation+task%2E+In+Proceedings+of+the+22nd+Inte)
29. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICLR 2015, Conference Track Proceedings. [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Jimmy+Ba%2E+2015%2E+Adam%3A+A+method+for+stochastic+optimization%2E+In+ICLR+2015%2C+Conference+Track+Proceedings%2E)
30. Rosa YG Paccotacya-Yanque, Candy A Huanca-Anquise, Judith Escalante-Calcina, Wilber R Ramos-Lovón, and Álvaro E Cuno-Parari. 2022. A speech corpus of quechua collao for automatic dimensional emotion recognition. Scientific Data, 9(1):778. [find](https://scholar.google.com/scholar?q=Rosa+YG+Paccotacya%2DYanque%2C+Candy+A+Huanca%2DAnquise%2C+Judith+Escalante%2DCalcina%2C+Wilber+R+Ramos%2DLov%C3%B3n%2C+and+%C3%81lvaro+E+Cuno%2DParari%2E+2022%2E+A+speech+corpus+of+quechua+collao+for+automatic+dimensional+emotion+r)
31. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+et+al%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E19437%2E)
32. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318. [find](https://scholar.google.com/scholar?q=Kishore+Papineni%2C+Salim+Roukos%2C+Todd+Ward%2C+and+Wei%2DJing+Zhu%2E+2002%2E+Bleu%3A+a+method+for+automatic+evaluation+of+machine+translation%2E+In+Proceedings+of+the+40th+annual+meeting+of+the+Association+for+Comp) [our card](https://md.research.elamur.ai/free/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
33. Edward Ma. 2019. Nlp augmentation. [https://github.com/makcedward/nlpaug](https://github.com/makcedward/nlpaug). [↗](https://github.com/makcedward/nlpaug)
34. Shuming Ma, Li Dong, Shaohan Huang, Dongdong Zhang, Alexandre Muzio, Saksham Singhal, Hany Hassan Awadalla, Xia Song, and Furu Wei. 2021. Deltalm: Encoder-decoder pre-training for language generation and translation by augmenting pretrained multilingual encoders. arXiv preprint arXiv:2106.13736. — [arXiv:2106.13736](https://arxiv.org/abs/2106.13736) [find](https://scholar.google.com/scholar?q=Shuming+Ma%2C+Li+Dong%2C+Shaohan+Huang%2C+Dongdong+Zhang%2C+Alexandre+Muzio%2C+Saksham+Singhal%2C+Hany+Hassan+Awadalla%2C+Xia+Song%2C+and+Furu+Wei%2E+2021%2E+Deltalm%3A+Encoder%2Ddecoder+pre%2Dtraining+for+language+generation+)
35. Yifan Peng, Jinchuan Tian, Brian Yan, Dan Berrebbi, Xuankai Chang, Xinjian Li, Jiatong Shi, Siddhant Arora, William Chen, Roshan Sharma, Wangyou Zhang, Yui Sudo, Muhammad Shakeel, Jee-Weon Jung, Soumi Maiti, and Shinji Watanabe. 2023. Reproducing whisper-style training using an open-source toolkit a… [find](https://scholar.google.com/scholar?q=Yifan+Peng%2C+Jinchuan+Tian%2C+Brian+Yan%2C+Dan+Berrebbi%2C+Xuankai+Chang%2C+Xinjian+Li%2C+Jiatong+Shi%2C+Siddhant+Arora%2C+William+Chen%2C+Roshan+Sharma%2C+Wangyou+Zhang%2C+Yui+Sudo%2C+Muhammad+Shakeel%2C+Jee%2DWeon+Jung%2C+Soumi)
36. Jonathan Mbuya and Antonios Anastasopoulos. 2023. GMU systems for the IWSLT 2023 dialect and low-resource speech translation tasks. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 269–276, Toronto, Canada (in-person and online). Association for… [find](https://scholar.google.com/scholar?q=Jonathan+Mbuya+and+Antonios+Anastasopoulos%2E+2023%2E+GMU+systems+for+the+IWSLT+2023+dialect+and+low%2Dresource+speech+translation+tasks%2E+In+Proceedings+of+the+20th+International+Conference+on+Spoken+Langua)
37. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine Mcleavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 28492–2… [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+Proceedings+of+the+40th+International+C) [our card](https://md.research.elamur.ai/free/papers/radford-2022-robust-speech-recognition-large-scale/)
38. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Noam+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N+Gomez%2C+%C5%81ukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+Advances+in+neural+information+processing+)
39. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1–67. [find](https://scholar.google.com/scholar?q=Colin+Raffel%2C+Noam+Shazeer%2C+Adam+Roberts%2C+Katherine+Lee%2C+Sharan+Narang%2C+Michael+Matena%2C+Yanqi+Zhou%2C+Wei+Li%2C+and+Peter+J%2E+Liu%2E+2020%2E+Exploring+the+limits+of+transfer+learning+with+a+unified+text%2Dto%2Dtex)
40. Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, Jiro Nishitoba, Yuya Unno, Nelson Enrique Yalta Soplin, Jahn Heymann, Matthew Wiesner, Nanxin Chen, Adithya Renduchintala, and Tsubasa Ochiai. 2018. ESPnet: End-to-end speech processing toolkit. In Proceedings of Interspeech, pages 2207–… [find](https://scholar.google.com/scholar?q=Shinji+Watanabe%2C+Takaaki+Hori%2C+Shigeki+Karita%2C+Tomoki+Hayashi%2C+Jiro+Nishitoba%2C+Yuya+Unno%2C+Nelson+Enrique+Yalta+Soplin%2C+Jahn+Heymann%2C+Matthew+Wiesner%2C+Nanxin+Chen%2C+Adithya+Renduchintala%2C+and+Tsubasa+Oc)
41. Jonathan Shen, Ruoming Pang, Ron J Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, Rj Skerrv-Ryan, et al. 2018. Natural tts synthesis by conditioning wavenet on mel spectrogram predictions. In 2018 IEEE international conference on acoustics, speech and signa… [find](https://scholar.google.com/scholar?q=Jonathan+Shen%2C+Ruoming+Pang%2C+Ron+J+Weiss%2C+Mike+Schuster%2C+Navdeep+Jaitly%2C+Zongheng+Yang%2C+Zhifeng+Chen%2C+Yu+Zhang%2C+Yuxuan+Wang%2C+Rj+Skerrv%2DRyan%2C+et+al%2E+2018%2E+Natural+tts+synthesis+by+conditioning+wavenet+)
42. Rodolfo Zevallos, Nuria Bel, Guillermo Cámbara, Mireia Farrús, and Jordi Luque. 2022a. Data augmentation for low-resource quechua asr improvement. arXiv preprint arXiv:2207.06872. — [arXiv:2207.06872](https://arxiv.org/abs/2207.06872) [find](https://scholar.google.com/scholar?q=Rodolfo+Zevallos%2C+Nuria+Bel%2C+Guillermo+C%C3%A1mbara%2C+Mireia+Farr%C3%BAs%2C+and+Jordi+Luque%2E+2022a%2E+Data+augmentation+for+low%2Dresource+quechua+asr+improvement%2E+arXiv+preprint+arXiv%3A2207%2E06872%2E+%E2%80%94+%5BarXiv%3A2207%2E06872%5D)
43. Rodolfo Zevallos, Luis Camacho, and Nelsi Melgarejo. 2022b. Huqariq: A multilingual speech corpus of native languages of peru forspeech recognition. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5029–5034. [find](https://scholar.google.com/scholar?q=Rodolfo+Zevallos%2C+Luis+Camacho%2C+and+Nelsi+Melgarejo%2E+2022b%2E+Huqariq%3A+A+multilingual+speech+corpus+of+native+languages+of+peru+forspeech+recognition%2E+In+Proceedings+of+the+Thirteenth+Language+Resources)
44. Jiatong Shi, William Chen, Dan Berrebbi, Hsiu-Hsuan Wang, Wei-Ping Huang, En-Pei Hu, Ho-Lam Chuang, Xuankai Chang, Yuxun Tang, Shang-Wen Li, Abdelrahman Mohamed, Hung-Yi Lee, and Shinji Watanabe. 2023. Findings of the 2023 ml-superb challenge: Pre-training and evaluation over more languages and beyo… [find](https://scholar.google.com/scholar?q=Jiatong+Shi%2C+William+Chen%2C+Dan+Berrebbi%2C+Hsiu%2DHsuan+Wang%2C+Wei%2DPing+Huang%2C+En%2DPei+Hu%2C+Ho%2DLam+Chuang%2C+Xuankai+Chang%2C+Yuxun+Tang%2C+Shang%2DWen+Li%2C+Abdelrahman+Mohamed%2C+Hung%2DYi+Lee%2C+and+Shinji+Watanabe%2E+2023)
45. Xiangyu Zhang, Qiquan Zhang, Hexin Liu, Tianyi Xiao, Xinyuan Qian, Beena Ahmed, Eliathamby Ambikairajah, Haizhou Li, and Julien Epps. 2024. Mamba in speech: Towards an alternative to self-attention. arXiv preprint arXiv:2405.12609. — [arXiv:2405.12609](https://arxiv.org/abs/2405.12609) [find](https://scholar.google.com/scholar?q=Xiangyu+Zhang%2C+Qiquan+Zhang%2C+Hexin+Liu%2C+Tianyi+Xiao%2C+Xinyuan+Qian%2C+Beena+Ahmed%2C+Eliathamby+Ambikairajah%2C+Haizhou+Li%2C+and+Julien+Epps%2E+2024%2E+Mamba+in+speech%3A+Towards+an+alternative+to+self%2Dattention%2E+a)
46. Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, et al. 2025. Openai gpt-5 system card. arXiv preprint arXiv:2601.03267. [find](https://scholar.google.com/scholar?q=Aaditya+Singh%2C+Adam+Fry%2C+Adam+Perelman%2C+Adam+Tart%2C+Adi+Ganesh%2C+Ahmed+El%2DKishky%2C+Aidan+McLaughlin%2C+Aiden+Low%2C+AJ+Ostrow%2C+Akhila+Ananthram%2C+et+al%2E+2025%2E+Openai+gpt%2D5+system+card%2E+arXiv+preprint+arXiv%3A26) [our card](https://md.research.elamur.ai/free/papers/singh-2025-openai-gpt-5-system-card/)