{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:43Z","timestamp":1774419403822,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890141","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation"],"prefix":"10.1109","author":[{"given":"Maohao","family":"Shen","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology"}]},{"given":"Shun","family":"Zhang","sequence":"additional","affiliation":[{"name":"AI at Meta"}]},{"given":"Jilong","family":"Wu","sequence":"additional","affiliation":[{"name":"AI at Meta"}]},{"given":"Zhiping","family":"Xiu","sequence":"additional","affiliation":[{"name":"AI at Meta"}]},{"given":"Ehab","family":"AlBadawy","sequence":"additional","affiliation":[{"name":"AI at Meta"}]},{"given":"Yiting","family":"Lu","sequence":"additional","affiliation":[{"name":"AI at Meta"}]},{"given":"Mike","family":"Seltzer","sequence":"additional","affiliation":[{"name":"AI at Meta"}]},{"given":"Qing","family":"He","sequence":"additional","affiliation":[{"name":"AI at Meta"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref2","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref3","article-title":"Measuring massive multitask language understanding","volume-title":"International Conference on Learning Representations","author":"Hendrycks"},{"key":"ref4","article-title":"Incorporating BERT into neural machine translation","volume-title":"International Conference on Learning Representations","author":"Zhu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1009"},{"key":"ref6","article-title":"NExT-GPT: Any-to-any multimodal llm","author":"Wu","year":"2023"},{"key":"ref7","article-title":"Any-to-any generation via composable diffusion","volume":"36","author":"Tang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"X-VILA: Cross-modality alignment for large language model","author":"Ye","year":"2024"},{"key":"ref9","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref10","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref11","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref15","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890588"},{"key":"ref17","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref20","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref23","article-title":"On generative spoken language modeling from raw audio","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref24","article-title":"VioLA: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023"},{"key":"ref25","article-title":"LauraGPT: Listen, attend, understand, and regenerate audio with gpt","author":"Chen","year":"2023"},{"key":"ref26","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref27","article-title":"Textually pretrained speech language models","volume":"36","author":"Hassid","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447112"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref30","article-title":"Spoken question answering and speech continuation using spectrogrampowered LLM","volume-title":"The Twelfth International Conference on Learning Representations","author":"Nachmani"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.438"},{"key":"ref32","article-title":"Spirit LM: Interleaved spoken and written language model","author":"Nguyen","year":"2024"},{"key":"ref33","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref34","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref35","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1063\/5.0203126"},{"key":"ref37","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447120"},{"key":"ref39","article-title":"GPQA: A graduate-level google-proof q&a benchmark","volume-title":"First Conference on Language Modeling","author":"Rein"},{"key":"ref40","article-title":"Think you have solved question answering? try ARC, the ai2 reasoning challenge","author":"Clark","year":"2018"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890141.pdf?arnumber=10890141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:42Z","timestamp":1774416162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890141","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}