{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T14:08:01Z","timestamp":1749650881191,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053053","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"8089-8093","source":"Crossref","is-referenced-by-count":19,"title":["Phoneme Boundary Detection Using Learnable Segmental Features"],"prefix":"10.1109","author":[{"given":"Felix","family":"Kreuk","sequence":"first","affiliation":[]},{"given":"Yaniv","family":"Sheena","sequence":"additional","affiliation":[]},{"given":"Joseph","family":"Keshet","sequence":"additional","affiliation":[]},{"given":"Yossi","family":"Adi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533865"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952591"},{"key":"ref13","first-page":"1233","article-title":"Real-time pitch determination of one or more voices by nonnegative matrix factorization","author":"sha","year":"2004","journal-title":"Proceeding of NIPS"},{"key":"ref14","article-title":"Timit acoustic phonetic continuous speech corpus","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium 1993"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367225"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.4906147"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.06.005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5772\/16433"},{"key":"ref28","article-title":"Automatic tools for analyzing spoken hebrew","author":"ben-shalom","year":"2014","journal-title":"Proc Afeka Speech Processing Conference"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.10.002"},{"key":"ref27","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324331"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960554"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607432"},{"key":"ref8","article-title":"On the relation between maximum spectral transition positions and phone boundaries","author":"dusan","year":"2006","journal-title":"ICSLP"},{"article-title":"Blind phoneme segmentation with temporal prediction errors","year":"2016","author":"michel","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.4972527"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2001.986241"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.05.002"},{"key":"ref20","article-title":"Phoneme alignment based on discriminative learning","author":"keshet","year":"2005","journal-title":"Ninth European Conference on Speech Communication and Technology"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639242"},{"key":"ref21","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":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-40"},{"key":"ref23","article-title":"Phoneme boundary detection using deep bidirectional LSTMs","author":"franke","year":"2016","journal-title":"Speech Communication 12 ITG Symposium Proceedings of VDE"},{"key":"ref26","article-title":"A tutorial on energy-based learning","volume":"1","author":"lecun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref25","first-page":"2282","article-title":"Structed: risk minimization in structured prediction","volume":"17","author":"adi","year":"2016","journal-title":"The Journal of Machine Learning Research"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053053.pdf?arnumber=9053053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:24:29Z","timestamp":1656375869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053053","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}