{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:37Z","timestamp":1775229997192,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446998","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12111-12115","source":"Crossref","is-referenced-by-count":13,"title":["Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition"],"prefix":"10.1109","author":[{"given":"Krishna C.","family":"Puvvada","sequence":"first","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Nithin","family":"Rao Koluguri","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Kunal","family":"Dhawan","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref8","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref9","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref10","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023"},{"key":"ref11","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref13","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref15","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref16","article-title":"High-fidelity audio compression with improved rvqgan","author":"Kumar","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref25","first-page":"28","article-title":"The ami meeting corpus: A pre-announcement","volume-title":"International workshop on machine learning for multimodal interaction","author":"Carletta"},{"key":"ref26","first-page":"7124","article-title":"Pyannote. audio: neural building blocks for speaker diarization","volume-title":"ICASSP 2020","author":"Bredin"},{"key":"ref27","article-title":"The nist speaker recognition evaluations: 1996 - 2001","volume-title":"2001: A Speaker Odyssey-The Speaker Recognition Workshop","author":"Martin"},{"key":"ref28","article-title":"Callhome american english speech","volume-title":"Linguistic Data Consortium","author":"Canavan"},{"key":"ref29","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref31","article-title":"Fisher spanish speech (ldc2010s01)","author":"Graff","year":"2010"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref33","article-title":"NeMo: a toolkit for Conversational AI and Large Language Models","author":"Harper"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446998.pdf?arnumber=10446998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:40:08Z","timestamp":1722573608000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446998","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}