{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T06:26:25Z","timestamp":1775715985820,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389705","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-8","source":"Crossref","is-referenced-by-count":69,"title":["On Decoder-Only Architecture For Speech-to-Text and Large Language Model Integration"],"prefix":"10.1109","author":[{"given":"Jian","family":"Wu","sequence":"first","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Long","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Yimeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Tianrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Bo","family":"Ren","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Linquan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Introducing chatgpt","year":"2022","journal-title":"OpenAI Blog"},{"key":"ref2","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","year":"2023"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv preprint arXiv:2204.02311"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref6","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Audiogpt: Understanding and generating speech, music, sound, and talking head","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2304.12995"},{"key":"ref8","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface","author":"Shen","year":"2023","journal-title":"arXiv preprint arXiv:2303.17580"},{"key":"ref9","article-title":"X-llm: Bootstrapping advanced large language models by treating multi-modalities as foreign languages","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv:2305.04160"},{"key":"ref10","article-title":"Pengi: An audio language model for audio tasks","author":"Deshmukh","year":"2023","journal-title":"arXiv preprint arXiv:2305.11834"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref12","article-title":"Minigpt-4: Enhancing visionlanguage understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv:2304.10592"},{"key":"ref13","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2304.08485"},{"key":"ref14","article-title":"Llama-adapter v2: Parameterefficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv preprint arXiv:2304.15010"},{"key":"ref15","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2305.16107"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref18","article-title":"Lms with a voice: Spoken language modeling beyond speech tokens","author":"Nachmani","year":"2023","journal-title":"arXiv preprint arXiv:2305.15255"},{"key":"ref19","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint arXiv:2306.12925"},{"key":"ref20","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref21","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref22","article-title":"Decoder-only or encoder-decoder? interpreting language model as a regularized encoder-decoder","author":"Fu","year":"2023","journal-title":"arXiv preprint arXiv:2304.04052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"ref24","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/iberspeech.2018-13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref27","article-title":"A weakly-supervised streaming multilingual speech model with truly zero-shot capability","author":"Xue","year":"2022","journal-title":"arXiv preprint arXiv:2211.02499"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2004"},{"key":"ref30","article-title":"Covost 2: A massively multilingual speech-to-text translation corpus","author":"Wang","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"issue":"1","key":"ref32","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref33","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","volume-title":"NIPS Workshop on End-to-end Learning for Speech and Audio Processing","author":"Berard"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref35","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref37","article-title":"Glu variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv preprint arXiv:2002.05202"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref39","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv:1711.05101"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref41","article-title":"Prompting large language models for zero-shot domain adaptation in speech recognition","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv:2306.16007"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389705.pdf?arnumber=10389705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T15:22:07Z","timestamp":1705936927000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389705","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}