{"id":"https://openalex.org/W2785572076","doi":"https://doi.org/10.1109/icassp.2018.8462223","title":"Spectral Distortion Model for Training Phase-Sensitive Deep-Neural Networks for Far-Field Speech Recognition","display_name":"Spectral Distortion Model for Training Phase-Sensitive Deep-Neural Networks for Far-Field Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2785572076","doi":"https://doi.org/10.1109/icassp.2018.8462223","mag":"2785572076"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara Sainath","raw_affiliation_strings":["Google Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Speech","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":"Arun Narayanan","raw_affiliation_strings":["Google Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Speech","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091715883","display_name":"Ananya Misra","orcid":null},"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":"Ananya Misra","raw_affiliation_strings":["Google Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Speech","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015892906","display_name":"R. C. Nongpiur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108356","display_name":"National Enterprise for NanoScience and NanoTechnology","ror":"https://ror.org/01sgfhb12","country_code":"IT","type":"facility","lineage":["https://openalex.org/I157210198","https://openalex.org/I162290304","https://openalex.org/I30771326","https://openalex.org/I4210087815","https://openalex.org/I4210108356","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rajeev Nongpiur","raw_affiliation_strings":["Nest"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nest","institution_ids":["https://openalex.org/I4210108356"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"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":"Michiel Bacchiani","raw_affiliation_strings":["Google Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Speech","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2013","issue":null,"first_page":"5729","last_page":"5733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.6735910177230835},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6428917646408081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6303380727767944},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5493375062942505},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5177654027938843},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4992821216583252},{"id":"https://openalex.org/keywords/near-and-far-field","display_name":"Near and far field","score":0.4937163293361664},{"id":"https://openalex.org/keywords/phase-distortion","display_name":"Phase distortion","score":0.4683004915714264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4522441625595093},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4138322174549103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32865065336227417},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.18419334292411804},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1027645468711853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09588921070098877},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07776200771331787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735910177230835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6428917646408081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6303380727767944},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5493375062942505},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5177654027938843},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4992821216583252},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.4937163293361664},{"id":"https://openalex.org/C57747864","wikidata":"https://www.wikidata.org/wiki/Q7180948","display_name":"Phase distortion","level":3,"score":0.4683004915714264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4522441625595093},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4138322174549103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32865065336227417},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18419334292411804},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1027645468711853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09588921070098877},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07776200771331787},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W118588063","https://openalex.org/W169229064","https://openalex.org/W587794757","https://openalex.org/W1566425957","https://openalex.org/W1586342741","https://openalex.org/W1600744878","https://openalex.org/W2034040413","https://openalex.org/W2041733487","https://openalex.org/W2062164080","https://openalex.org/W2063656732","https://openalex.org/W2064675550","https://openalex.org/W2083509110","https://openalex.org/W2117678320","https://openalex.org/W2130775302","https://openalex.org/W2136439176","https://openalex.org/W2160815625","https://openalex.org/W2213952365","https://openalex.org/W2326699523","https://openalex.org/W2396889049","https://openalex.org/W2398826216","https://openalex.org/W2400339399","https://openalex.org/W2512499206","https://openalex.org/W2517616541","https://openalex.org/W2589857635","https://openalex.org/W2617258110","https://openalex.org/W2622203030","https://openalex.org/W2702006285","https://openalex.org/W2749659773","https://openalex.org/W2766930522","https://openalex.org/W2963920996","https://openalex.org/W2964138484","https://openalex.org/W4244320231","https://openalex.org/W6617368339","https://openalex.org/W6635768407","https://openalex.org/W6665938000","https://openalex.org/W6679449663","https://openalex.org/W6688428952","https://openalex.org/W6712560600","https://openalex.org/W6739644732"],"related_works":["https://openalex.org/W2148464474","https://openalex.org/W2069896135","https://openalex.org/W2043217787","https://openalex.org/W2021411150","https://openalex.org/W1977296418","https://openalex.org/W2041160448","https://openalex.org/W2011693998","https://openalex.org/W2021338396","https://openalex.org/W2986127413","https://openalex.org/W1986191199"],"abstract_inverted_index":{"In":[0,113,141],"this":[1,136,156],"paper,":[2],"we":[3,117],"present":[4],"an":[5,119],"algorithm":[6,120],"which":[7,121],"introduces":[8,122],"phase-perturbation":[9],"to":[10,55,71,79,125,132],"the":[11,50,127],"training":[12,15,146],"database":[13],"when":[14],"phase-sensitive":[16],"deep":[17],"neural-network":[18],"models.":[19],"Traditional":[20],"features":[21,27,36,43,48],"such":[22,37,84],"as":[23,38,85],"log-mel":[24],"or":[25,40,66,105],"cepstral":[26],"do":[28],"not":[29],"have":[30,31,49],"any":[32],"phase-relevant":[33,45],"information.":[34,46],"However":[35],"raw-waveform":[39],"complex":[41],"spectra":[42],"contain":[44],"Phase-sensitive":[47],"advantage":[51],"of":[52,60,82,149],"being":[53],"able":[54],"detect":[56],"differences":[57],"in":[58,87],"time":[59],"arrival":[61],"across":[62],"different":[63],"microphone":[64,88],"channels":[65],"frequency":[67],"bands.":[68],"However,":[69],"compared":[70],"magnitude-based":[72,96],"features,":[73,97],"phase":[74],"information":[75],"is":[76,99],"more":[77,130],"sensitive":[78],"various":[80],"kinds":[81],"distortions":[83],"variations":[86],"characteristics,":[89],"reverberation,":[90,106],"and":[91,153,167],"so":[92],"on.":[93],"For":[94],"traditional":[95],"it":[98],"widely":[100],"known":[101],"that":[102],"adding":[103],"noise":[104],"often":[107],"called":[108],"Multistyle-TRaining":[109],"(MTR),":[110],"improves":[111],"robustness.":[112],"a":[114,145],"similar":[115],"spirit,":[116],"propose":[118],"spectral":[123],"distortion":[124],"make":[126],"deep-learning":[128],"models":[129],"robust":[131],"phase-distortion.":[133],"We":[134],"call":[135],"approach":[137,157],"Spectral-Distortion":[138],"TRaining":[139],"(SDTR).":[140],"our":[142],"experiments":[143],"using":[144],"set":[147],"consisting":[148],"22-million":[150],"utterances":[151],"with":[152],"without":[154],"MTR,":[155],"reduces":[158],"Word":[159],"Error":[160],"Rates":[161],"(WERs)":[162],"relatively":[163],"by":[164],"3.2":[165],"%":[166,169],"8.48":[168],"respectively":[170],"on":[171,175],"test":[172],"sets":[173],"recorded":[174],"Google":[176],"Home.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}