{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:15:41Z","timestamp":1740100541234,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"European Research Council (ERC)","doi-asserted-by":"publisher","award":["694537"],"award-info":[{"award-number":["694537"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688123","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"267-274","source":"Crossref","is-referenced-by-count":2,"title":["On Architectures and Training for Raw Waveform Feature Extraction in ASR"],"prefix":"10.1109","author":[{"given":"Peter","family":"Vieting","sequence":"first","affiliation":[{"name":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"}]},{"given":"Christoph","family":"Luscher","sequence":"additional","affiliation":[{"name":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"}]},{"given":"Wilfried","family":"Michel","sequence":"additional","affiliation":[{"name":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"}]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[{"name":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"}]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[{"name":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"}]}],"member":"263","reference":[{"key":"ref33","article-title":"RE-TURNN as a generic flexible neural toolkit with application to translation and speech recognition","author":"zeyer","year":"2018","journal-title":"Annual Meeting of the Assoc for Computational Linguis-tics"},{"key":"ref32","article-title":"RE-TURNN: the RWTH extensible training framework for universal recurrent neural networks","author":"doetsch","year":"2017","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854207"},{"key":"ref30","article-title":"RASR - the RWTH Aachen University open source speech recognition toolkit","author":"rybach","year":"2011","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref34","article-title":"Conformer: Convolution-augmented transformer for speech recog-nition","author":"gulati","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref11","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref12","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"ref15","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Representation Learning Work-shop Int Conf on Machine Learning (ICML)"},{"key":"ref16","article-title":"Phoneme based neural transducer for large vo-cabulary speech recognition","author":"zhou","year":"2021","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682273"},{"key":"ref19","article-title":"Fast, sim-pler and more accurate hybrid ASR systems using word-pieces","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"LSTM language models for LVCSR in first-pass decoding and lattice-rescoring","author":"beck","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"890","DOI":"10.21437\/Interspeech.2014-223","article-title":"Acoustic modeling with deep neural networks using raw time signal for LVCSR","author":"t\u00fcske","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053169"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref5","first-page":"4295","article-title":"Convolutional neural networks-based contin-uous speech recognition using raw speech signal","author":"palaz","year":"0","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461871"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00337016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.399052"},{"key":"ref21","first-page":"649","article-title":"Gam-matone features and feature combination for large vo-cabulary speech recognition","author":"schl\u00fcter","year":"2007","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref23","first-page":"754","article-title":"Cumulative adaptation for BLSTM acoustic mod-els","author":"kitza","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-2"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688123.pdf?arnumber=9688123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T21:11:36Z","timestamp":1726607496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688123","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}