{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:38:17Z","timestamp":1730198297216,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023184","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"page":"655-661","source":"Crossref","is-referenced-by-count":0,"title":["Can We Simulate Generative Process of Acoustic Modeling Data? Towards Data Restoration for Acoustic Modeling"],"prefix":"10.1109","author":[{"given":"Ryo","family":"Masumura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Ijima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Kobashikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takanobu","family":"Oba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yushi","family":"Aono","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"22","article-title":"VoiceRex spontaneous speech recognition technology for contact-center conversations","volume":"5","author":"masataki","year":"2007","journal-title":"NTT Technical Review"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889790"},{"key":"ref31","first-page":"947","article-title":"Spontaneous speech corpus of Japanese","author":"maekawa","year":"0","journal-title":"Proc Int Conference on Language Resources and Evaluation (LREC)"},{"key":"ref30","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"0","journal-title":"Proc Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1217"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2400218"},{"key":"ref11","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"0","journal-title":"Proc Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref13","first-page":"4470","article-title":"Unidirectional long short-term memory recurrent nenural network with recurrent output layer for low-latency speech synthesis","author":"zen","year":"0","journal-title":"Proc International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref14","first-page":"8012","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref16","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","author":"jaitly","year":"0","journal-title":"ICML Workshop on Deep Learning for Audio Speech and Language Processing"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"ref18","first-page":"810","article-title":"Data augmentation for low resource languages","author":"ragni","year":"0","journal-title":"Proc Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref19","first-page":"1420","article-title":"Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages","author":"tuske","year":"0","journal-title":"Proc Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref28","article-title":"Cycle-consistency training for end-to-end speech recognition","author":"hori","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495596"},{"key":"ref27","first-page":"477","article-title":"Lever-aging sequence-to-sequence speech synthesis for enhancing acoustic-to-word speech recognition","author":"mimura","year":"0","journal-title":"Proc IEEE\/ACL Workshop Spoken Lang Technol (SLT)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2010.01.029"},{"key":"ref6","article-title":"Roles of pre-training and fine-tuning in context-dependent DBN-HMMs for real-world speech recognition","author":"yu","year":"0","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2215588"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref7","first-page":"437","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"0","journal-title":"Proc Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref9","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"0","journal-title":"Proc Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref1","first-page":"2083","article-title":"A big data approach to acoustic model training corpus selection","author":"kapralova","year":"0","journal-title":"Proc Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1109\/TASLP.2015.2438544","article-title":"Data augmentation for deep neural network acoustic modeling","volume":"23","author":"cui","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref21","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"0","journal-title":"Proc Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282225"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268911"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2019,11,18]]},"location":"Lanzhou, China","end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023184.pdf?arnumber=9023184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:52:55Z","timestamp":1658094775000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023184","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}