{"id":"https://openalex.org/W1542280630","doi":"https://doi.org/10.1109/icassp.2015.7178847","title":"Speech acoustic modeling from raw multichannel waveforms","display_name":"Speech acoustic modeling from raw multichannel waveforms","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1542280630","doi":"https://doi.org/10.1109/icassp.2015.7178847","mag":"1542280630"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047455929","display_name":"Yedid Hoshen","orcid":"https://orcid.org/0000-0002-0967-4541"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yedid Hoshen","raw_affiliation_strings":["Hebrew University of Jerusalem, Jerusalem, Israel","Hebrew University of Jerusalem,\u00a0Israel"],"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"Hebrew University of Jerusalem,\u00a0Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google Inc., New York, NY, USA","Google Inc., New York, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin W. Wilson","raw_affiliation_strings":["Google Inc., New York, NY, USA","Google Inc., New York, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047455929"],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":40.0585,"has_fulltext":false,"cited_by_count":231,"citation_normalized_percentile":{"value":0.99789449,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4624","last_page":"4628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5426999926567078,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5426999926567078,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4023999869823456,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.017100000753998756,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.8670607805252075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8033756017684937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.637460470199585},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6124065518379211},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5604483485221863},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5438637137413025},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5370728969573975},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5226083397865295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5044821500778198},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4838079810142517},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47762244939804077},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4757273495197296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46023961901664734},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1418544054031372},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13535332679748535}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8670607805252075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033756017684937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.637460470199585},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6124065518379211},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5604483485221863},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5438637137413025},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5370728969573975},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5226083397865295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5044821500778198},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4838079810142517},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47762244939804077},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4757273495197296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46023961901664734},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1418544054031372},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13535332679748535},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.682.4827","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.682.4827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/43290.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1734538896","https://openalex.org/W1969851134","https://openalex.org/W1989314204","https://openalex.org/W2009150118","https://openalex.org/W2061074721","https://openalex.org/W2096496615","https://openalex.org/W2096980176","https://openalex.org/W2101045344","https://openalex.org/W2103088716","https://openalex.org/W2132037657","https://openalex.org/W2146502635","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2408093180","https://openalex.org/W2616139854","https://openalex.org/W2963175699","https://openalex.org/W6637242042","https://openalex.org/W6675646395","https://openalex.org/W6678409544","https://openalex.org/W6681435938","https://openalex.org/W6684191040","https://openalex.org/W6713548365"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2883092465","https://openalex.org/W2114441484"],"abstract_inverted_index":{"Standard":[0],"deep":[1,30],"neural":[2,27,31],"network-based":[3],"acoustic":[4,34,183],"models":[5],"for":[6],"automatic":[7],"speech":[8],"recognition":[9],"(ASR)":[10],"rely":[11],"on":[12,145,174],"hand-engineered":[13],"input":[14,99],"features,":[15],"typically":[16],"log-mel":[17,190],"filterbank":[18,83,121,191],"magnitudes.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"describe":[24],"a":[25,51,106,120,133,175,186],"convolutional":[26,112],"network":[28,32,66,156],"-":[29],"(CNN-DNN)":[33],"model":[35,117,184],"which":[36],"takes":[37],"raw":[38],"multichannel":[39,93,177],"waveforms":[40],"as":[41],"input,":[42],"i.e.":[43,132],"without":[44],"any":[45],"preceding":[46],"feature":[47,53],"extraction,":[48],"and":[49,128,196],"learns":[50,119,157],"similar":[52],"representation":[54],"through":[55],"supervised":[56],"training.":[57],"By":[58],"operating":[59],"directly":[60],"in":[61,108,125,165],"the":[62,65,73,115,155,166,170,181],"time":[63,76],"domain,":[64],"is":[67,79,88,123],"able":[68],"to":[69,104,158,169],"take":[70],"advantage":[71],"of":[72,114,130,135],"signal's":[74],"fine":[75],"structure":[77,87],"that":[78,122,180,188],"discarded":[80],"when":[81,91],"computing":[82],"magnitude":[84,192],"features.":[85],"This":[86],"especially":[89],"useful":[90],"analyzing":[92],"inputs,":[94],"where":[95],"timing":[96],"differences":[97],"between":[98],"channels":[100],"can":[101],"be":[102],"used":[103],"localize":[105],"signal":[107],"space.":[109],"The":[110],"first":[111],"layer":[113],"proposed":[116,182],"naturally":[118],"selective":[124],"both":[126],"frequency":[127,141],"direction":[129],"arrival,":[131],"bank":[134],"bandpass":[136],"beamformers":[137],"with":[138,148],"an":[139],"auditory-like":[140],"scale.":[142],"When":[143],"trained":[144],"data":[146],"corrupted":[147],"noise":[149,171],"coming":[150],"from":[151],"different":[152],"spatial":[153],"locations,":[154],"filter":[159],"them":[160],"out":[161],"by":[162],"steering":[163],"nulls":[164],"directions":[167],"corresponding":[168],"sources.":[172],"Experiments":[173],"simulated":[176],"dataset":[178],"show":[179],"outperforms":[185],"DNN":[187],"uses":[189],"features":[193],"under":[194],"noisy":[195],"reverberant":[197],"conditions.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":49},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":30},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}