{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:57:00Z","timestamp":1764399420130,"version":"3.46.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249339","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"843-848","source":"Crossref","is-referenced-by-count":0,"title":["VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription"],"prefix":"10.1109","author":[{"given":"Nguyen Quoc","family":"Anh","sequence":"first","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernard","family":"Cheng","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kelvin","family":"Soh","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv preprint"},{"volume-title":"Dali: A large dataset of synchronized audio, lyrics and notes, automatically created using teacher-student machine learning paradigm.","year":"2018","author":"Meseguer-Brocal","key":"ref2"},{"key":"ref3","article-title":"Lyricwhiz: Robust multilingual zero-shot lyrics transcription by whispering to chatgpt","author":"Zhuo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096725"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2378"},{"volume-title":"The MUSDB18 corpus for music separation","year":"2017","author":"Rafii","key":"ref6"},{"volume-title":"Law no. 07\/2022\/qh15 of june 16, 2022, amending and supplementing a number of articles of the law on intellectual property, viet nam, wipo lex","key":"ref7"},{"volume-title":"10 fastest spoken languages in the world","year":"2024","author":"Da\u011f","key":"ref10"},{"key":"ref11","article-title":"Contrastive learning of musical representations","volume":"abs\/2103.09410","author":"Spijkervet","year":"2021","journal-title":"CoRR"},{"key":"ref12","first-page":"387","volume-title":"Evaluation of algorithms using games: The case of music tagging.","author":"Law","year":"2009"},{"key":"ref13","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"abs\/2006.11477","author":"Baevski","year":"2020","journal-title":"CoRR"},{"volume-title":"Nguyenvulebinh\/wav2vec2-base-vi-hugging face","author":"Nguyen","key":"ref14"},{"volume-title":"Vlsp2020 asr dataset","author":"Anh","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13050977"},{"volume-title":"Thangtrungnguyen\/vietnamese-female-male-voice-classification-model, hugging face","author":"Nguyen","key":"ref17"},{"volume-title":"Thangtrungnguyen\/vietnamese-regional-voice-classification-model, hugging face","author":"Nguyen","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"volume-title":"HuggingFace, Openai\u2019s whisper model card","year":"2024","key":"ref20"},{"key":"ref21","article-title":"PhoWhisper: Automatic Speech Recognition for Vietnamese","volume-title":"Proceedings of the ICLR2024 Tiny Papers track","author":"Le","year":"2024"},{"volume-title":"Lyrics transcription for humans: A readability-aware benchmark","year":"2024","author":"C\u00edfka","key":"ref22"},{"volume-title":"Batmanofzuhandarrgh\/vietlyrics: Vietlyrics: A large-scale dataset and models for vietnamese automatic lyrics transcription","key":"ref23"},{"volume-title":"Nguyen Quoc Anh, Vietnamese automatic lyrics transcription -whisper-large-v2","year":"2024","author":"Soh","key":"ref24"},{"volume-title":"Vietnamese automatic lyrics transcription -whisper-medium","year":"2024","author":"Soh","key":"ref25"},{"volume-title":"Vietnamese automatic lyrics transcription -whisper-large-v2","year":"2024","author":"Soh","key":"ref26"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249339.pdf?arnumber=11249339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:54:25Z","timestamp":1764399265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249339","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}