{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T22:50:50Z","timestamp":1777243850264,"version":"3.51.4"},"reference-count":63,"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"}],"funder":[{"DOI":"10.13039\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389676","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":38,"title":["Reproducing Whisper-Style Training Using An Open-Source Toolkit And Publicly Available Data"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Peng","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Yan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Berrebbi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinjian","family":"Li","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhant","family":"Arora","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roshan","family":"Sharma","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yui","family":"Sudo","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Shakeel","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jee-Weon","family":"Jung","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumi","family":"Maiti","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","volume-title":"Proc. NeurIPS","author":"Vaswani"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref3","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021","journal-title":"arXiv:2112.11446"},{"key":"ref4","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv:2204.02311"},{"key":"ref5","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref6","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref7","article-title":"GPT-4 Technical Report","volume-title":"arXiv:2303.08774","year":"2023"},{"key":"ref8","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022399"},{"key":"ref15","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv:2212.04356"},{"key":"ref16","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021","journal-title":"arXiv:2104.02133"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref18","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv:2303.01037"},{"key":"ref19","article-title":"Towards understanding and mitigating social biases in language models","volume-title":"Proc. ICML","author":"Liang"},{"key":"ref20","article-title":"On the robustness of chatgpt: An adversarial and out-of-distribution perspective","author":"Wang","year":"2023","journal-title":"arXiv:2302.12095"},{"key":"ref21","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023","journal-title":"arXiv:2303.12712"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1860"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1233"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref34","article-title":"Common voice: A massivelymultilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv:1912.06670"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.1992.225858"},{"key":"ref36","article-title":"Improved speech-to-text translation with the fisher and callhome Spanish-English speech translation corpus","author":"Post","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023141"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/app10196936"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-729"},{"key":"ref40","article-title":"ReazonSpeech: A Free and Massive Corpus for Japanese ASR","author":"Yin","year":"2023"},{"key":"ref41","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit","author":"Yamagishi","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953075"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref47","article-title":"Pytorch: An imperative style, highperformance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref49","article-title":"Branchformer: Parallel MLP-attention architectures to capture local and global context for speech recognition and understanding","volume-title":"Proc. ICML","author":"Peng"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref51","article-title":"Squeezeformer: An efficient transformer for automatic speech recognition","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1194"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096135"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref56","article-title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","volume-title":"Proc. NeurIPS","author":"Jeff Lai"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095780"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1213"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096662"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1105"},{"key":"ref63","article-title":"A survey of machine unlearning","author":"Nguyen","year":"2022","journal-title":"arXiv:2209.02299"}],"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\/10389676.pdf?arnumber=10389676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:30:16Z","timestamp":1707157816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389676","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}