{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:59:47Z","timestamp":1775199587868,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434598","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-4","source":"Crossref","is-referenced-by-count":0,"title":["WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction"],"prefix":"10.1109","author":[{"given":"Jakaria Islam","family":"Emon","sequence":"first","affiliation":[{"name":"Hokkaido Denshikiki Co., Ltd.,Sapporo,Japan"}]},{"given":"Md. Abu","family":"Salek","sequence":"additional","affiliation":[{"name":"Hokkaido Denshikiki Co., Ltd.,Sapporo,Japan"}]},{"given":"Kazi Tamanna","family":"Alam","sequence":"additional","affiliation":[{"name":"Barisal Information Technology College,Department of Computer Science and Engineering,Barisal,Bangladesh"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint arXiv:2301.11325"},{"key":"ref2","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2301.12503"},{"key":"ref3","article-title":"Fast timingconditioned latent audio diffusion","volume-title":"Forty-first International Conference on Machine Learning","author":"Evans"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890307"},{"key":"ref5","first-page":"1061","article-title":"SSL-MOS: A Self-Supervised Learning Based Approach with A Transformer Target Model For MOS Prediction","volume-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE","author":"Jiang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref8","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford"},{"key":"ref9","article-title":"Qwen technical report","volume-title":"arXiv preprint arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21251"},{"key":"ref11","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.437"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/864"},{"key":"ref16","article-title":"High fidelity text-guided music generation and editing via single-stage flow matching","author":"Le Lan","year":"2024","journal-title":"arXiv preprint arXiv:2407.03648"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447265"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.132"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2158"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888241"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1524"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.436"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434598.pdf?arnumber=11434598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:56:27Z","timestamp":1775192187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434598","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}