{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:31:45Z","timestamp":1753601505818,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095363","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labels"],"prefix":"10.1109","author":[{"given":"Tzeviya Sylvia","family":"Fuchs","sequence":"first","affiliation":[{"name":"Bar-Ilan University,Ramat-Gan,Israel"}]},{"given":"Yedid","family":"Hoshen","sequence":"additional","affiliation":[{"name":"The Hebrew University of Jerusalem"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479543"},{"key":"ref12","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":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/1267352"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11474"},{"key":"ref10","first-page":"1082","article-title":"Unsupervised spoken term discovery using wav2vec 2.0","author":"iwamoto","year":"2021","journal-title":"2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.05.001"},{"key":"ref1","article-title":"An improved speech segmentation quality measure: the r-value","author":"r\u00e4s\u00e4nen","year":"2009","journal-title":"Tenth Annual Conference of the International Speech Communication Association"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2398"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620800"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-1874","article-title":"Segmental contrastive predictive coding for unsupervised word segmentation","author":"bhati","year":"2021"},{"article-title":"Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words","year":"2021","author":"cuervo","key":"ref9"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1109\/ASRU.2017.8269008","article-title":"An embedded segmental k-means model for unsupervised segmentation and clustering of speech","author":"kamper","year":"2017","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-1738","article-title":"Unsupervised discovery of recurring speech patterns using probabilistic adaptive metrics","author":"r\u00e4s\u00e4nen","year":"2020"},{"article-title":"Towards unsupervised phone and word segmentation using selfsupervised vector-quantized neural networks","year":"2020","author":"kamper","key":"ref6"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.csl.2017.04.008","article-title":"A segmental framework for fully-unsupervised largevocabulary speech recognition","volume":"46","author":"kamper","year":"2017","journal-title":"Computer Speech & Language"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095363.pdf?arnumber=10095363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:56:49Z","timestamp":1699901809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095363","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}