{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T05:01:46Z","timestamp":1729659706749,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472622","type":"proceedings-article","created":{"date-parts":[[2016,6,23]],"date-time":"2016-06-23T21:58:30Z","timestamp":1466719110000},"page":"4965-4969","source":"Crossref","is-referenced-by-count":12,"title":["A deep scattering spectrum \u2014 Deep Siamese network pipeline for unsupervised acoustic modeling"],"prefix":"10.1109","author":[{"given":"Neil","family":"Zeghidour","sequence":"first","affiliation":[]},{"given":"Gabriel","family":"Synnaeve","sequence":"additional","affiliation":[]},{"given":"Maarten","family":"Versteegh","sequence":"additional","affiliation":[]},{"given":"Emmanuel","family":"Dupoux","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1142\/S0218001493000339","article-title":"Signature verification using a siamese time delay neural network","volume":"7","author":"jane","year":"1993","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref12","first-page":"2208","article-title":"Learning phonetic categories by learning a lexicon","author":"feldman","year":"2009","journal-title":"Proceedings of the 31st Annual Conference of the Cognitive Science Society"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1620"},{"key":"ref14","first-page":"93","article-title":"The darpa speech recognition research database: specifications and status","author":"fisher","year":"1986","journal-title":"Proc DARPA Workshop on Speech Recognition"},{"key":"ref15","article-title":"The zero resource speech challenge 2015","author":"versteegh","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref16","article-title":"Buckeye corpus of conversational speech (2nd release)","author":"pitt","year":"2007","journal-title":"www buckeyecorpus osu edu"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.specom.2013.07.001","article-title":"A smartphone-based asr data collection tool for under-resourced languages","volume":"56","author":"de vries","year":"2014","journal-title":"Speech Communication"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref19","article-title":"A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling","author":"thiolli\u00e8re","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref4","article-title":"A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge","author":"renshaw","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref3","article-title":"Discovering discrete subword units with binarized autoencoders and hidden-markov-model encoders","author":"badino","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2326991"},{"key":"ref5","article-title":"Weakly supervised multi-embeddings learning of acoustic models","author":"synnaeve","year":"2014","journal-title":"ICLRE"},{"key":"ref8","first-page":"1","article-title":"Evaluating speech features with the minimal-pair abx task: Analysis of the classical mfc\/plp pipeline","author":"schatz","year":"2013","journal-title":"14th Annual Conference of the International Speech Communication Association Interspeech 2013"},{"key":"ref7","article-title":"Analysis of cnn-based speech recognition system using raw speech as input","author":"palaz","year":"0","journal-title":"Proceedings of Interspeech 2015 number EPFL-CONF-210029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078558"},{"key":"ref1","article-title":"A summary of the 2012 JH CLSP Workshop on zero resource speech technologies and models of early language acquisition","author":"jansen","year":"2013","journal-title":"Proceedings of ICASSP"},{"key":"ref9","article-title":"Evaluating speech features with the minimal-pair abx task (ii): Resistance to noise","author":"schatz","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref20","article-title":"Parallel inference of dirichlet process gaussian mixture models for unsupervised acoustic modeling: A feasibility study","author":"chen","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853588"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2016,3,20]]},"location":"Shanghai","end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472622.pdf?arnumber=7472622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T13:00:26Z","timestamp":1498309226000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472622","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}