{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:19Z","timestamp":1776885499029,"version":"3.51.2"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746102","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3189-3193","source":"Crossref","is-referenced-by-count":16,"title":["Contrastive Prediction Strategies for Unsupervised Segmentation and Categorization of Phonemes and Words"],"prefix":"10.1109","author":[{"given":"Santiago","family":"Cuervo","sequence":"first","affiliation":[{"name":"University of Wroclaw,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maciej","family":"Grabias","sequence":"additional","affiliation":[{"name":"University of Wroclaw,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Chorowski","sequence":"additional","affiliation":[{"name":"NavAlgo,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grzegorz","family":"Ciesielski","sequence":"additional","affiliation":[{"name":"University of Wroclaw,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Lancucki","sequence":"additional","affiliation":[{"name":"Nvidia,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pawel","family":"Rychlikowski","sequence":"additional","affiliation":[{"name":"University of Wroclaw,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ricard","family":"Marxer","sequence":"additional","affiliation":[{"name":"Université de Toulon, Aix Marseille Univ,Cnrs, LIS,Toulon,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-538"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"1929","article-title":"Dropout: A simple way to pre-vent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","article-title":"The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","author":"nguyen","year":"2020"},{"key":"ref4","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"CoRR"},{"key":"ref3","article-title":"Towards un-supervised phone and word segmentation using self-supervised vector-quantized neural networks","author":"kamper","year":"2020","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1544"},{"key":"ref8","article-title":"Darpa timit acoustic phonetic continuous speech corpus cdrom","author":"garofolo","year":"1993"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1874"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2398"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746102.pdf?arnumber=9746102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:13:18Z","timestamp":1661199198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746102","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}