{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:29:53Z","timestamp":1729643393416,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383597","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"201-208","source":"Crossref","is-referenced-by-count":1,"title":["Incorporating Discriminative DPGMM Posteriorgrams for Low-Resource ASR"],"prefix":"10.1109","author":[{"given":"Bin","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.032"},{"article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","year":"2016","author":"wu","key":"ref38"},{"article-title":"Using the output embedding to improve language models","year":"2016","author":"press","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3207"},{"key":"ref36","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"International Conference on Machine Learning"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2977776"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref12","article-title":"A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge","author":"renshaw","year":"2015","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855085"},{"key":"ref14","article-title":"Discovering discrete subword units with binarized Autoencoders and Hidden-Markov-Model encoders","author":"badino","year":"2015","journal-title":"InterSpeech"},{"key":"ref15","article-title":"A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling","author":"thiolliere","year":"2015","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3232"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68456-7_14"},{"key":"ref18","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","author":"lee","year":"2012","journal-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.033"},{"key":"ref28","article-title":"Conjugate Bayesian analysis of the Gaussian distribution","author":"murphy","year":"2007","journal-title":"Technical Report"},{"key":"ref4","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref27","first-page":"639","article-title":"A constructive definition of dirichlet priors","author":"sethuraman","year":"1994","journal-title":"Statistica Sinica"},{"key":"ref3","article-title":"Fundamentals of speech recognition","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/ASRU.2017.8269011","article-title":"Feature optimized DPGMM clustering for unsupervised subword modeling: A contribution to Zerospeech 2017","author":"heck","year":"2017","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref29","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI Technical Report"},{"key":"ref5","article-title":"HTK: Hidden Markov model toolkit v1. 5","author":"young","year":"1993","journal-title":"User Manual"},{"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":"InterSpeech"},{"key":"ref7","article-title":"Parallel inference of Dirichlet process Gaussian mixture models for unsupervised acoustic modeling: A feasibility study","author":"chen","year":"2015","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref9","article-title":"The zero resource speech challenge 2015","author":"versteegh","year":"2015","journal-title":"InterSpeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1160"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1168654"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1337"},{"key":"ref42","first-page":"280","article-title":"Dirichlet process","author":"teh","year":"2010","journal-title":"Encyclopedia of Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415149"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-97","article-title":"Analysis and comparison of recent mlp features for lvcsr systems","author":"valente","year":"2011","journal-title":"InterSpeech"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383597.pdf?arnumber=9383597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T13:16:29Z","timestamp":1671714989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383597\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383597","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}