{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:07Z","timestamp":1774419367315,"version":"3.50.1"},"reference-count":51,"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\/icassp49660.2025.10888073","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Audio Diffusion with Large Language Models"],"prefix":"10.1109","author":[{"given":"Yinghui","family":"Huang","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Kastner","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kartik","family":"Audhkhasi","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Statistical methods for speech recognition.","author":"Jelinek","year":"1998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref7","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref8","article-title":"Prompting large language models with speech recognition abilities","author":"Fathullah","year":"2023"},{"key":"ref9","article-title":"An embarrassingly simple approach for llm with strong asr capacity","author":"Ma","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446898"},{"key":"ref11","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Kong","year":"2024"},{"key":"ref12","first-page":"23 716","article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"Proc. NeurIPS","volume":"35","author":"Alayrac"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1616"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096429"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref17","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref18","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"Chen","year":"2020"},{"key":"ref19","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. NeurIPS","volume":"35","author":"Wei"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","article-title":"Subtractive training for music stem insertion using latent diffusion models","author":"Villa-Renteria","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref23","article-title":"Polyffusion: A diffusion model for polyphonic score generation with internal and external controls","author":"Min","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3694969"},{"key":"ref26","first-page":"8489","article-title":"Reduce, reuse, recycle: Compositional generation with energy-based diffusion models and mcmc","volume-title":"Proc. ICML","author":"Du"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095118"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10974"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1929"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3186162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746453"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389803"},{"key":"ref34","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024"},{"key":"ref35","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024"},{"key":"ref36","article-title":"Spirit-lm: Interleaved spoken and written language model","author":"Nguyen","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832146"},{"key":"ref38","article-title":"Massively multilingual neural machine translation in the wild: Findings and challenges","author":"Arivazhagan","year":"2019"},{"key":"ref39","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref40","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho","year":"2020"},{"issue":"47","key":"ref41","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref42","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref44","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref45","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"CoRR","author":"Ardila","year":"2019"},{"key":"ref46","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref48","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NeurIPS","volume":"35","author":"Saharia"},{"key":"ref49","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"ref50","first-page":"13 213","article-title":"simple diffusion: End-to-end diffusion for high resolution images","volume-title":"Proc. ICML","author":"Hoogeboom"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"}],"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\/10888073.pdf?arnumber=10888073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:31Z","timestamp":1774416151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888073","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}