{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T07:34:30Z","timestamp":1780385670924,"version":"3.54.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413711","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"196-200","source":"Crossref","is-referenced-by-count":34,"title":["CDPAM: Contrastive Learning for Perceptual Audio Similarity"],"prefix":"10.1109","author":[{"given":"Pranay","family":"Manocha","sequence":"first","affiliation":[{"name":"Princeton University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Adobe Research,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Finkelstein","sequence":"additional","affiliation":[{"name":"Princeton University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"The interspeech 2020 deep noise suppression challenge: Datasets, subjective speech quality and testing framework","author":"reddy","year":"0"},{"key":"ref38","article-title":"Can we automatically transform speech recorded on common consumer devices in real-world environments into professional production quality speech?—a dataset, insights, and challenges","author":"mysore","year":"2014","journal-title":"SPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109381"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683654"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref37","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","author":"valentini-botinhao","year":"2017"},{"key":"ref36","article-title":"The LJ speech dataset","author":"ito","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.12.006"},{"key":"ref34","article-title":"The voice conversion challenge 2018","author":"lorenzo-trueba","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref11","article-title":"Are disentangled representations helpful for abstract visual reasoning?","author":"steenkiste","year":"2019","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Towards a definition of disentangled representations","author":"higgins","year":"2018"},{"key":"ref13","article-title":"Robustness of speech quality metrics: Comparing ViSQOL, PESQ and POLQA","author":"hines","year":"2013","journal-title":"ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461965"},{"key":"ref15","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461524"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053442"},{"key":"ref19","article-title":"Learning disentangled representations for timber and pitch in music audio","author":"hung","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073702"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0054-9"},{"key":"ref6","first-page":"26","article-title":"Learning with learned loss function: Speech enhancement with quality-net","volume":"27","author":"fu","year":"2019","journal-title":"SPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682367"},{"key":"ref5","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","author":"patton","year":"2016","journal-title":"NIPS Workshop"},{"key":"ref8","article-title":"SESQA: semi-supervised learning for speech quality assessment","author":"serr\u00e0","year":"2020"},{"key":"ref7","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"0"},{"key":"ref2","article-title":"Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment","author":"rix","year":"2001","journal-title":"ICASSP"},{"key":"ref9","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref22","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2922832"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref23","article-title":"Audio Albert: A lite BERT for self-supervised learning of audio representation","author":"chi","year":"2020"},{"key":"ref26","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2398"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413711.pdf?arnumber=9413711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:52Z","timestamp":1659485992000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413711","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}