{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T20:57:09Z","timestamp":1729630629444,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414649","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6883-6887","source":"Crossref","is-referenced-by-count":0,"title":["Representation Learning for Speech Recognition Using Feedback Based Relevance Weighting"],"prefix":"10.1109","author":[{"given":"Purvi","family":"Agrawal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178855"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-464","article-title":"Mean Hilbert envelope coefficients (MHEC) for robust speaker recognition","author":"sadjadi","year":"2012","journal-title":"Proc of Interspeech"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288820"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref11","article-title":"Interpretable convolutional filters with SincNet","author":"ravanelli","year":"2018","journal-title":"Proc of Neural Information Processing Systems (NIPS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref13","first-page":"1607","article-title":"Data-driven design of RASTA-like filters","volume":"1","author":"vuuren","year":"1997","journal-title":"Eurospeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857801"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760373"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2913965"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030489"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref19","article-title":"The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"hirsch","year":"2000","journal-title":"ASR2000-Automatic Speech Recognition Challenges for the new Millenium ISCA Tutorial and Research Workshop (ITRW)"},{"key":"ref28","article-title":"PyTorch","volume":"1","author":"paszke","year":"2017","journal-title":"Computer software Vers 0 3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707746"},{"key":"ref27","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc of ICML"},{"key":"ref3","first-page":"1766","article-title":"Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks","author":"palaz","year":"2013","journal-title":"Proceedings of Interspeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"},{"journal-title":"IEEE ASRU","year":"2011","author":"povey","key":"ref29"},{"key":"ref5","first-page":"890","article-title":"Acoustic modeling with deep neural networks using raw time signal for LVCSR","author":"t\u00fcske","year":"2014","journal-title":"Proc of Interspeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472808"},{"key":"ref7","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref2","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc of International Conference on Learning Representations (ICLR)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2652"},{"key":"ref1","first-page":"2579","article-title":"Visualizing data using t-sne","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref22","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1837"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2301"},{"key":"ref26","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv preprint arXiv 1607 08022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414649.pdf?arnumber=9414649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:29:28Z","timestamp":1672129768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414649","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}