{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:00:57Z","timestamp":1775199657607,"version":"3.50.1"},"reference-count":49,"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\/asru65441.2025.11434625","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":["QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems"],"prefix":"10.1109","author":[{"given":"Chien-Chun","family":"Wang","sequence":"first","affiliation":[{"name":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"}]},{"given":"Kuan-Tang","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"}]},{"given":"Cheng-Yeh","family":"Yang","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Dept. 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 Computer Science Academia Sinica,Taiwan"}]},{"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"}]}],"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094628"},{"key":"ref3","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. ICML","author":"Ju"},{"key":"ref4","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 arXiv:2406.05370"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"ref6","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proc. ICML","author":"Huang"},{"key":"ref7","article-title":"SoundStorm: Efficient parallel audio generation","author":"Borsos","year":"2023","journal-title":"Arxiv preprint arXiv:2305.09636"},{"key":"ref8","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref9","article-title":"Simple and controllable music generation","volume-title":"Proc. NeurIPS","author":"Copet"},{"key":"ref10","article-title":"Noise2Music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023","journal-title":"Arxiv preprint arXiv:2302.03917"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3597493"},{"key":"ref12","article-title":"ERNIE-music: Text-to-waveform music generation with diffusion models","volume-title":"Proc. AACL Demo","author":"Zhu"},{"key":"ref13","article-title":"MuseCoco: Generating symbolic music from text","author":"Lu","year":"2023","journal-title":"Arxiv preprint arXiv:2306.00110"},{"key":"ref14","article-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023","journal-title":"Arxiv preprint arXiv:2301.11757"},{"key":"ref15","article-title":"Masked audio generation using a single nonautoregressive transformer","volume-title":"Proc. ICLR","author":"Ziv"},{"key":"ref16","article-title":"Fr\u00e9chet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2019","journal-title":"Arxiv preprint arXiv:1812.08466"},{"key":"ref17","article-title":"A note on the inception score","volume-title":"Proc. ICML","author":"Barratt"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890307"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref22","article-title":"Self-supervised speech quality estimation and enhancement wsing only clean speech","volume-title":"Proc. ICLR","author":"Fu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3644692"},{"key":"ref24","article-title":"Predicting accurate probabilities with a ranking loss","volume-title":"Proc. ICML","author":"Menon"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01105"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00535"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01218"},{"key":"ref28","article-title":"A ranking-based, balanced loss function unifying classification and localisation in object detection","volume-title":"Proc. NeurIPS","author":"Oksuz"},{"key":"ref29","article-title":"PiRank: Scalable learning to rank via differentiable sorting","volume-title":"Proc. NeurIPS","author":"Swezey"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449794"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00300"},{"key":"ref32","article-title":"Rethinking and reweighting the univariate losses for multi-label ranking: Consistency and generalization","volume-title":"Proc. NeurIPS","author":"Wu"},{"key":"ref33","article-title":"Post-training quantization for vision transformer","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref34","article-title":"Benchmarking deep AUROC optimization: Loss functions and algorithmic choices","author":"Zhu","year":"2022","journal-title":"Arxiv preprint arXiv:2203.14177"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599851"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296062"},{"key":"ref37","article-title":"A unified framework for rankbased loss minimization","volume-title":"Proc. NeurIPS","author":"Xiao"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_6"},{"key":"ref39","article-title":"Pairwise ranking loss for multi-task learning in recommender systems","author":"Durmus","year":"2024","journal-title":"Arxiv preprint arXiv:2406.02163"},{"key":"ref40","article-title":"Offline model-based optimization by learning to rank","volume-title":"Proc. ICLR","author":"Tan"},{"key":"ref41","article-title":"Enhancing knowledge distillation of large language models through efficient multi-modal distribution alignment","volume-title":"Proc. COLING","author":"Peng"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0029"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref44","first-page":"81","article-title":"From RankNet to LambdaRank to LambdaMART: An overview","volume":"11","author":"Burges","year":"2010","journal-title":"Learning"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref47","article-title":"Meta audiobox aesthetics: Unified automatic quality assessment for speech, music, and sound","author":"Tjandra","year":"2025","journal-title":"Arxiv preprint arXiv:2502.05139"},{"key":"ref48","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2017","journal-title":"Arxiv preprint arXiv:1609.04747"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"}],"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\/11434625.pdf?arnumber=11434625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:25Z","timestamp":1775192245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434625","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}