{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:09:55Z","timestamp":1772910595084,"version":"3.50.1"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832148","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"863-870","source":"Crossref","is-referenced-by-count":1,"title":["ESPnet-EZ: Python-Only ESPnet For Easy Fine-Tuning And Integration"],"prefix":"10.1109","author":[{"given":"Masao","family":"Someki","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwanghee","family":"Choi","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":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jionghao","family":"Han","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Peng","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":"Vaibhav","family":"Srivastav","sequence":"additional","affiliation":[{"name":"Hugging Face,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":"The Kaldi Speech Recognition Toolkit","volume-title":"Proc. ASRU","author":"Povey"},{"key":"ref2","volume-title":"sox(1) Linux User\u2019s Manual, Free Software Foundation","author":"Bagwell"},{"key":"ref3","article-title":"awk(1) Linux User\u2019s Manual","volume-title":"Free Software Foundation","author":"Aho"},{"key":"ref4","volume-title":"Linux User\u2019s Manual, Free Software Foundation","author":"Morse"},{"key":"ref5","volume-title":"SCTK, the NIST Scoring Toolkit","author":"Fiscus"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref8","article-title":"ESPnet2-TTS: Extending the edge of tts research","volume-title":"arXiv preprint arXiv:2110.07840","author":"Hayashi"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10039"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10727"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096977"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1345"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.38"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389628"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/VCCBC.2020-26"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1176"},{"key":"ref22","article-title":"Unsupervised speech recognition","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref23","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1194"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1938"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.549"},{"key":"ref28","article-title":"UniverSLU: Universal spoken language understanding for diverse classification and sequence generation tasks with a single network","volume-title":"Proc. ACL","author":"Arora"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447112"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref32","article-title":"MLSUPERB 2.0: Benchmarking multilingual speech models across modeling constraints, languages, and datasets","volume-title":"Proc. Interspeech","author":"Shi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref34","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. ICML","author":"Hu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747908"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747236"},{"key":"ref40","volume-title":"Python Software Foundation, Python Package Index (PyPI)"},{"key":"ref41","volume-title":"Anaconda Software Distribution"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04101"},{"key":"ref43","article-title":"Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurements","volume-title":"Proc. EMNLP","author":"Werra"},{"key":"ref44","article-title":"Hugging-face\u2019s transformers: State-of-the-art natural language processing","volume-title":"arXiv preprint arXiv:1910.03771","author":"Wolf"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1673"},{"key":"ref46","article-title":"NeMo: a toolkit for building AI applications using Neural Modules","volume-title":"arXiv preprint arXiv:1909.09577","author":"Kuchaiev"},{"key":"ref47","article-title":"SpeechBrain: A General-Purpose Speech Toolkit","volume-title":"arXiv preprint arXiv:2106.04624","author":"Ravanelli"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref49","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.21"},{"key":"ref51","article-title":"Lhotse: a speech data representation library for the modern deep learning ecosystem","volume-title":"arXiv preprint arXiv:2110.12561","author":"\u017celasko"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref54","article-title":"Decoupled Weight Decay Regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.119"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"ref59","article-title":"A study of translation edit rate with targeted human annotation","volume-title":"Proc. AMTA","author":"Snover"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref61","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume-title":"JMLR","author":"Raffel"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393714"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref69","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","volume-title":"Univ. of Edinburgh. Centre for Speech Technology Research","author":"Yamagishi"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4770"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832148.pdf?arnumber=10832148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:26Z","timestamp":1737398366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832148","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}