Elamur Research⌕
☰
home / papers / 2025 / Distilling an End-to-End Voice Assistant Without Instruction Training Data

Distilling an End-to-End Voice Assistant Without Instruction Training Data

Paper · 2025 · William Held, Yanzhe Zhang, Minzhi Li et al.

Summary

End-to-end Speech LLMs are usually built with supervised finetuning on speech instruction data. That data is scarce, often recorded by few speakers, and the resulting models tend to lose abilities inherited from their text-only backbone. The authors propose the Distilled Voice Assistant (DiVA), which needs no annotated instruction responses. It uses only ASR data from CommonVoice: speech paired with transcripts. The frozen text LLM's own reaction to each transcript serves as the training target.

The model connects a Whisper-Large-v3 encoder to a frozen Llama 3 8B through a Q-Former whose weights are initialized from the Whisper decoder. Training combines two losses:

  • an L2 loss pulling audio-derived embeddings toward the LLM's text input embeddings;
  • a cheaper reformulation of KL-divergence distillation on the output distribution.

Although it sees only transcription data, DiVA handles spoken question answering, classification, emotion recognition and translation. In a user preference study it also beats Qwen 2 Audio, while using far less compute. The work shows that LLMs can be adapted to speech cheaply, without collecting new instruction datasets, using open, permissively licensed data.

Key points

  • Training data: about 3.5k hours of CommonVoice only, compared with roughly 4.4k to over 370k hours for baselines such as SALMONN, Qwen Audio, Qwen 2 Audio and UltraVox.
  • In user preference trials, DiVA beat Qwen 2 Audio 72% of the time, despite needing more than 100x less training compute.
  • The authors' KL objective lowers distillation cost from O(V·d) to O(d), and adding input-side (L2) distillation is central to following instructions. On translation, outputs were in the correct target language 74% of the time, versus 1.4% for an output-distillation-only model (FastText language ID).
  • Ablations on the connector:
    • Training the Q-Former from scratch instead of from Whisper decoder weights drops QA from 55.17 to 47.63.
    • Replacing the Q-Former with an MLP drops QA to 29.48 and classification to 33.85.
  • Limitations: DiVA can only learn speech signals that share information with transcripts, which limits paralinguistic cues. It was evaluated only on single-turn interactions, and it inherits biases from the base LLM. Models, data and full training code are open-sourced.

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, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

Cite

Cite as William Held, Yanzhe Zhang, Minzhi Li, Weiyan Shi, Michael J Ryan and Diyi Yang. 2025. Distilling an End-to-End Voice Assistant Without Instruction Training Data. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.acl-long.388

@inproceedings{held2025distilling,
  title = {{Distilling an End-to-End Voice Assistant Without Instruction Training Data}},
  author = {William Held, Yanzhe Zhang, Minzhi Li, Weiyan Shi, Michael J Ryan and Diyi Yang},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.388},
  url = {https://doi.org/10.18653/v1/2025.acl-long.388}
}

References

68 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Robin N Brewer, Christina Harrington, and Courtney Heldreth. 2023. Envisioning equitable speech technologies for black older adults. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, pages 379–388. find
  2. Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N Chang, Sungbok Lee, and Shrikanth S Narayanan. 2008. Iemocap: Interactive emotional dyadic motion capture database. Language resources and evaluation, 42:335–359. find
  3. Xiangrui Cai, Haidong Xu, Sihan Xu, Ying Zhang, and Xiaojie Yuan. 2022. Badprompt: Backdoor attacks on continuous prompts. Preprint, arXiv:2211.14719. — [arXiv:2211.14719](https://arxiv.org/abs/2211.14719) find
  4. Santiago Castro, Devamanyu Hazarika, Verónica Pérez-Rosas, Roger Zimmermann, Rada Mihalcea, and Soujanya Poria. 2019. Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4619– 4629, Flo…
  5. May Pik Yu Chan, June Choe, Aini Li, Yiran Chen, Xin Gao, and Nicole R Holliday. 2022. Training and typological bias in asr performance for world englishes. In INTERSPEECH, pages 1273–1277. find
  6. Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, and 1 others. 2021a. Gigaspeech: An evolving, multi-domain asr corpus with 10,000 hours of transcribed audio. arXiv preprint arXiv:2106.06909. find
  7. Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, and 1 others. 2022. WavLM: Large-scale Self-supervised Pre-training for Full Stack Speech Processing. IEEE Journal of Selected Topics in Signal Processing, 16(6):1505–1518. find
  8. Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, and 1 others. 2021. Speecht5: Unified-modal encoder-decoder pre-training for spoken language processing. arXiv preprint arXiv:2110.07205.
  9. Yi-Chen Chen, Po-Han Chi, Shu-wen Yang, Kai-Wei Chang, Jheng-hao Lin, Sung-Feng Huang, Da-Rong Liu, Chi-Liang Liu, Cheng-Kuang Lee, and Hung-yi Lee. 2021b. Speechnet: A universal modularized model for speech processing tasks. arXiv preprint arXiv:2105.03070. — [arXiv:2105.03070](https://arxiv.org/abs/2105.03070) find
  10. Rosana Ardila, Megan Branson, Kelly Davis, Michael Henretty, Michael Kohler, Josh Meyer, Reuben Morais, Lindsay Saunders, Francis M Tyers, and Gregor Weber. 2019. CommonVoice: A Massively-Multilingual Speech Corpus. arXiv preprint arXiv:1912.06670.
  11. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* Chat-GPT Quality. find
  12. 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.
  13. Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, Chang Zhou, and Jingren Zhou. 2024. Qwen2-Audio Technical Report. Preprint, arXiv:2407.10759.
  14. Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919.
  15. Jonathan H Clark, Eunsol Choi, Michael Collins, Dan Garrette, Tom Kwiatkowski, Vitaly Nikolaev, and Jennimaria Palomaki. 2020. TydiAa: A Benchmark for Information-seeking Question Answering in Typologically Diverse Languages. Transactions of the Association for Computational Linguistics, 8:454– 470. find
  16. Christophe Coupé, Yoon Mi Oh, Dan Dediu, and François Pellegrino. 2019. Different languages, similar encoding efficiency: Comparable information rates across the human communicative niche. Science advances, 5(9):eaaw2594. find
  17. Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. Preprint, arXiv:2305.06500.
  18. Soham Deshmukh, Benjamin Elizalde, Rita Singh, and Huaming Wang. 2023. Pengi: An audio language model for audio tasks. Advances in Neural Information Processing Systems, 36:18090–18108. find
  19. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, and 516 others. 202… — The Llama 3 Herd of Models
  20. Jacob Eisenstein, Vinodkumar Prabhakaran, Clara Rivera, Dorottya Demszky, and Devyani Sharma. 2023. Md3: The multi-dialect dataset of dialogues. arXiv preprint arXiv:2305.11355. — [arXiv:2305.11355](https://arxiv.org/abs/2305.11355) find
  21. Fahim Faisal, Sharlina Keshava, Antonios Anastasopoulos, and 1 others. 2021. Sd-qa: Spoken dialectal question answering for the real world. arXiv preprint arXiv:2109.12072. find
  22. Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Ke Li, Jinxi Guo, Wenhan Xiong, Jay Mahadeokar, Ozlem Kalinli, and 1 others. 2024. Prompting Large Language Models with Speech Recognition Abilities. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and… find
  23. Daniel Galvez, Greg Diamos, Juan Ciro, Juan Felipe Cerón, Keith Achorn, Anjali Gopi, David Kanter, Maximilian Lam, Mark Mazumder, and Vijay Janapa Reddi. 2021. The People’s Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage. arXiv preprint arXiv:2111.09344. — [arXiv:2111.09344](https://arxiv.org/abs/2111.09344) find
  24. Shefali Garg, Zhouyuan Huo, Khe Chai Sim, Suzan Schwartz, Mason Chua, Alëna Aksënova, Tsendsuren Munkhdalai, Levi King, Darryl Wright, Zion Mengesha, and 1 others. 2023. Improving speech recognition for african american english with audio classification. arXiv preprint arXiv:2309.09996.
  25. Yuan Gong, Yu-An Chung, and James Glass. 2021. AST: Audio Spectrogram Transformer. arXiv preprint arXiv:2104.01778. find
  26. Yuan Gong, Hongyin Luo, Alexander H Liu, Leonid Karlinsky, and James Glass. 2023. Listen, think, and understand. arXiv preprint arXiv:2305.10790. — [arXiv:2305.10790](https://arxiv.org/abs/2305.10790) find
  27. Md Kamrul Hasan, Wasifur Rahman, AmirAli Bagher Zadeh, Jianyuan Zhong, Md Iftekhar Tanveer, Louis-Philippe Morency, and Mohammed (Ehsan) Hoque. 2019. UR-FUNNY: A Multimodal Language Dataset for Understanding Humor. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Proces… find
  28. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015a. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
  29. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015b. Distilling the knowledge in a neural network. Preprint, arXiv:1503.02531.
  30. Chao-Chun Hsu, Sheng-Yeh Chen, Chuan-Chun Kuo, Ting-Hao Huang, and Lun-Wei Ku. 2018. Emotion-Lines: An Emotion Corpus of Multi-Party Conversations. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources A… find
  31. Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. HuBERT: Self-supervised Speech Representation Learning by Masked Prediction of Hidden Units. IEEE/ACM transactions on audio, speech, and language processing, 29:3451– 3460.
  32. Tahir Javed, Sakshi Joshi, Vignesh Nagarajan, Sai Sundaresan, Janki Nawale, Abhigyan Raman, Kaushal Bhogale, Pratyush Kumar, and Mitesh M Khapra. 2023. Svarah: Evaluating english asr systems on indian accents. arXiv preprint arXiv:2305.15760.
  33. Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2017. Bag of Tricks for Efficient Text Classification. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 427–431, Valencia, Spain. Associatio… find
  34. Seokhwan Kim, Yang Liu, Di Jin, Alexandros Papangelis, Karthik Gopalakrishnan, Behnam Hedayatnia, and Dilek Hakkani-Tür. 2021. “how robust ru?”: Evaluating task-oriented dialogue systems on spoken conversations. In 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 1147–… find
  35. Allison Koenecke, Andrew Nam, Emily Lake, Joe Nudell, Minnie Quartey, Zion Mengesha, Connor Toups, John R Rickford, Dan Jurafsky, and Sharad Goel. 2020. Racial disparities in automated speech recognition. Proceedings of the National Academy of Sciences, 117(14):7684–7689. find
  36. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023a. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. Preprint, arXiv:2301.12597.
  37. Xinjian Li, Shinnosuke Takamichi, Takaaki Saeki, William Chen, Sayaka Shiota, and Shinji Watanabe. 2023b. YODAS: Youtube-Oriented Dataset for Audio and Speech. In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 1–8. IEEE. find
  38. Zongxia Li, Ishani Mondal, Yijun Liang, Huy Nghiem, and Jordan Lee Boyd-Graber. 2024. Pedants: Cheap but effective and interpretable answer equivalence. Preprint, arXiv:2402.11161. find
  39. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023a. Improved Baselines with Visual Instruction Tuning. Preprint, arXiv:2310.03744.
  40. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. Visual Instruction Tuning. In NeurIPS.
  41. Potsawee Manakul, Guangzhi Sun, Warit Sirichotedumrong, Kasima Tharnpipitchai, and Kunat Pipatanakul. 2024. Enhancing low-resource language and instruction following capabilities of audio language models. Preprint, arXiv:2409.10999. — [arXiv:2409.10999](https://arxiv.org/abs/2409.10999) find
  42. Zion Mengesha, Courtney Heldreth, Michal Lahav, Juliana Sublewski, and Elyse Tuennerman. 2021. “i don’t think these devices are very culturally sensitive.”—impact of automated speech recognition errors on african americans. Frontiers in Artificial Intelligence, 4:725911. find
  43. John X. Morris, Wenting Zhao, Justin T. Chiu, Vitaly Shmatikov, and Alexander M. Rush. 2023. Language Model Inversion. Preprint, arXiv:2311.13647. 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pages 5206– 5210. IEEE. — [arXiv:2311.13647](https://arxiv.org/abs/2311.13647) find
  44. Yifan Peng, Jinchuan Tian, William Chen, Siddhant Arora, Brian Yan, Yui Sudo, Muhammad Shakeel, Kwanghee Choi, Jiatong Shi, Xuankai Chang, and 1 others. 2024. Owsm v3. 1: Better and faster open whisper-style speech models based on e-branchformer. arXiv preprint arXiv:2401.16658. — [arXiv:2401.16658](https://arxiv.org/abs/2401.16658) find
  45. Yifan Peng, Jinchuan Tian, Brian Yan, Dan Berrebbi, Xuankai Chang, Xinjian Li, Jiatong Shi, Siddhant Arora, William Chen, Roshan Sharma, and 1 others. 2023. Reproducing whisper-style training using an open-source toolkit and publicly available data. In 2023 IEEE Automatic Speech Recognition and Unde… find
  46. Bilal Porgali, Vítor Albiero, Jordan Ryda, Cristian Canton Ferrer, and Caner Hazirbas. 2023. The casual conversations v2 dataset. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10–17. find
  47. Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria, and Rada Mihalcea. 2019. MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 527– 536, Flore…
  48. Matt Post. 2018. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186– 191, Brussels, Belgium. Association for Computational Linguistics.
  49. Vineel Pratap, Qiantong Xu, Anuroop Sriram, Gabriel Synnaeve, and Ronan Collobert. 2020. MLS: A Large-Scale Multilingual Dataset for Speech Research. InterSpeech.
  50. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. Preprint, arXiv:2103.00020.
  51. Jesse Mu, Xiang Lisa Li, and Noah Goodman. 2024. Learning to compress prompts with gist tokens. Preprint, arXiv:2304.08467.
  52. 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.
  53. Christine Murad, Cosmin Munteanu, Benjamin R Cowan, and Leigh Clark. 2019. Revolution or evolution? speech interaction and hci design guidelines. IEEE Pervasive Computing, 18(2):33–45. find
  54. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250.
  55. Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. 2015. LibriSpeech: an ASR Corpus Based on Public Domain Audio Books. In Sherry Ruan, Jacob O Wobbrock, Kenny Liou, Andrew Ng, and James A Landay. 2018. Comparing speech and keyboard text entry for short messages in two languages on… find
  56. Yu Shu, Siwei Dong, Guangyao Chen, Wenhao Huang, Ruihua Zhang, Daochen Shi, Qiqi Xiang, and Yemin Shi. 2023. Llasm: Large language and speech model. arXiv preprint arXiv:2308.15930. — [arXiv:2308.15930](https://arxiv.org/abs/2308.15930) find
  57. Charlie Snell, Dan Klein, and Ruiqi Zhong. 2022. Learning by distilling context. Preprint, arXiv:2209.15189. find
  58. 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.
  59. Paden Tomasello, Akshat Shrivastava, Daniel Lazar, Po-Chun Hsu, Duc Le, Adithya Sagar, Ali Elkahky, Jade Copet, Wei-Ning Hsu, Yossi Adi, and 1 others. 2023. Stop: A dataset for spoken task oriented semantic parsing. In 2022 IEEE Spoken Language Technology Workshop (SLT), pages 991–998. IEEE. find
  60. Pooja Upadhyay, Sharon Heung, Shiri Azenkot, and Robin N Brewer. 2023. Studying exploration & long-term use of voice assistants by older adults. In Proceedings of the 2023 CHI conference on human factors in computing systems, pages 1–11. find
  61. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2023. Attention is all you need. Preprint, arXiv:1706.03762.
  62. Changhan Wang, Anne Wu, and Juan Pino. 2020. CoVoST 2: A Massively Multilingual Speech-to-Text Translation Corpus. Preprint, arXiv:2007.10310. find
  63. Chen Wang, Minpeng Liao, Zhongqiang Huang, Jinliang Lu, Junhong Wu, Yuchen Liu, Chengqing Zong, and Jiajun Zhang. 2024. Blsp: Bootstrapping language-speech pre-training via behavior alignment of continuation writing. Preprint, arXiv:2309.00916.
  64. Mingqiu Wang, Wei Han, Izhak Shafran, Zelin Wu, Chung-Cheng Chiu, Yuan Cao, Nanxin Chen, Yu Zhang, Hagen Soltau, Paul K Rubenstein, and 1 others. 2023. Slm: Bridge the thin gap between speech and text foundation models. In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pag…
  65. Jian Wu, Yashesh Gaur, Zhuo Chen, Long Zhou, Yimeng Zhu, Tianrui Wang, Jinyu Li, Shujie Liu, Bo Ren, Linquan Liu, and 1 others. 2023. On decoder-only architecture for speech-to-text and large language model integration. In 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pag… find
  66. Yijing Wu, SaiKrishna Rallabandi, Ravisutha Srinivasamurthy, Parag Pravin Dakle, Alolika Gon, and Preethi Raghavan. 2024. Heysquad: A spoken question answering dataset. Preprint, arXiv:2304.13689. — [arXiv:2304.13689](https://arxiv.org/abs/2304.13689) find
  67. Shuwen Yang, Heng-Jui Chang, Zili Huang, Andy T. Liu, Cheng-I Lai, Haibin Wu, Jiatong Shi, Xuankai Chang, Hsiang-Sheng Tsai, Wen-Chin Huang, Tzu hsun Feng, Po-Han Chi, Yist Y. Lin, Yung-Sung Chuang, Tzu-Hsien Huang, Wei-Cheng Tseng, Kushal Lakhotia, Shang-Wen Li, Abdelrahman Mohamed, and 2 others. 2… — [arXiv:2404.09385](https://arxiv.org/abs/2404.09385) find
  68. Dong Zhang, Shimin Li, Xin Zhang, Jun Zhan, Pengyu Wang, Yaqian Zhou, and Xipeng Qiu. 2023. SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities. Preprint, arXiv:2305.11000.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/held-2025-distilling-end-end-voice-assistant/