{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:22:05Z","timestamp":1764400925067,"version":"3.46.0"},"reference-count":29,"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\/apsipaasc65261.2025.11249325","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"2038-2043","source":"Crossref","is-referenced-by-count":0,"title":["DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction"],"prefix":"10.1109","author":[{"given":"Cheng-Yeh","family":"Yang","sequence":"first","affiliation":[{"name":"National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan"}]},{"given":"Kuan-Tang","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan"}]},{"given":"Chien-Chun","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan"}]},{"given":"Hung-Shin","family":"Lee","sequence":"additional","affiliation":[{"name":"United Link Co., Ltd.,Taiwan"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica,Taiwan"}]},{"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref2","article-title":"Masked audio generation using a single non-autoregressive transformer","volume-title":"Proc. ICLR","author":"Ziv","year":"2024"},{"key":"ref3","article-title":"VALL-E 2: Neural codec language models are human parity zero-shot text to speech synthesizers","author":"Chen","year":"2024","journal-title":"Arxiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref6","article-title":"Fr\u00e9chet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2019","journal-title":"Arxiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1496"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/s23031203"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023304"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890307"},{"key":"ref17","article-title":"Meta audiobox aesthetics: Unified automatic quality assessment for speech, music, and sound","author":"Tjandra","year":"2025","journal-title":"Arxiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2616"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1422"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053217"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref26","article-title":"GhostVLAD for setbased face recognition","volume-title":"Proc. ACCV","author":"Zhong","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.554"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.499"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"}],"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\/11249325.pdf?arnumber=11249325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:20:05Z","timestamp":1764400805000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249325","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}