{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:34Z","timestamp":1760245054995,"version":"3.44.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683851","type":"proceedings-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T16:07:22Z","timestamp":1555430842000},"page":"6470-6474","source":"Crossref","is-referenced-by-count":8,"title":["PyHTK: Python Library and ASR Pipelines for HTK"],"prefix":"10.1109","author":[{"given":"C.","family":"Zhang","sequence":"first","affiliation":[{"name":"Engineering Dept., Cambridge University, Cambridge, CB2 1PZ, U.K."}]},{"given":"F.L.","family":"Kreyssig","sequence":"additional","affiliation":[{"name":"Engineering Dept., Cambridge University, Cambridge, CB2 1PZ, U.K."}]},{"given":"Q.","family":"Li","sequence":"additional","affiliation":[{"name":"Engineering Dept., Cambridge University, Cambridge, CB2 1PZ, U.K."}]},{"given":"P.C.","family":"Woodland","sequence":"additional","affiliation":[{"name":"Engineering Dept., Cambridge University, Cambridge, CB2 1PZ, U.K."}]}],"member":"263","reference":[{"year":"0","key":"ref38"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.21437\/Interspeech.2016-275"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.21437\/Interspeech.2016-595"},{"year":"2014","author":"kingma","article-title":"Adam: A method for stochastic optimization","key":"ref31"},{"key":"ref30","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from over-fitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref37","article-title":"The MGB challenge: Evaluating multi-genre broadcast media transcription","author":"bell","year":"2015","journal-title":"Proc ASRU"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.21437\/Interspeech.2018-2335"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/ICASSP.2016.7472805"},{"key":"ref34","article-title":"Unfolded recurrent neural networks for speech recognition","author":"saon","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref10","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"0","journal-title":"Proc OSDI"},{"key":"ref11","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NIPS Autodiff Workshop"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1162\/neco.1997.9.8.1735"},{"year":"2014","author":"chung","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/5.726791"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP.2015.7178776"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2017.7953111"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP.2019.8683373"},{"key":"ref18","article-title":"Acoustic modeling with deep neural networks using raw time signal for LVCSR","author":"t\u00fcske","year":"2014","journal-title":"Proc Inter-speech"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TASLP.2016.2558826"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP.2002.1005687"},{"key":"ref28","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc ICML"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1006\/csla.1995.0010"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.21437\/Interspeech.2018-1423"},{"year":"2015","author":"young","journal-title":"The HTK book (for HTK version 3 5)","key":"ref6"},{"key":"ref5","article-title":"A general artificial neural network extension for HTK","author":"zhang","year":"2015","journal-title":"Proc INTERSPEECH"},{"year":"2015","author":"ioffe","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","key":"ref29"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP.2017.7953177"},{"key":"ref7","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.3115\/1075812.1075885"},{"key":"ref9","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014","journal-title":"Microsoft Technical Report MSR-TR-2014-112"},{"year":"0","key":"ref1"},{"key":"ref20","article-title":"Self-normalizing neural networks","author":"klambauer","year":"2017","journal-title":"Proc NIPS"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.21437\/Interspeech.2018-2432"},{"year":"0","author":"ramachandran","article-title":"Searching for activation functions","key":"ref21"},{"key":"ref24","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICASSP.2018.8461608"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1145\/1143844.1143891"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/ICASSP.2018.8462523"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683851.pdf?arnumber=8683851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:07:23Z","timestamp":1757095643000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683851","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}