{"id":"https://openalex.org/W3011199534","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023011","title":"Investigation of Monaural Front-End Processing for Robust Speech Recognition Without Retraining or Joint-Training","display_name":"Investigation of Monaural Front-End Processing for Robust Speech Recognition Without Retraining or Joint-Training","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011199534","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023011","mag":"3011199534"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"254"},"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":0.9998999834060669,"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":0.9997000098228455,"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":0.8067853450775146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.720599889755249},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.617767333984375},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5701532363891602},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5649713277816772},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5569446682929993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48203814029693604},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45741480588912964},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42411917448043823},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3350095748901367},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08670663833618164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8067853450775146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.720599889755249},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.617767333984375},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5701532363891602},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5649713277816772},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5569446682929993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48203814029693604},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45741480588912964},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42411917448043823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3350095748901367},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08670663833618164},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1897240248","https://openalex.org/W1989364685","https://openalex.org/W1992475611","https://openalex.org/W2008971146","https://openalex.org/W2013598660","https://openalex.org/W2031647436","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2073612610","https://openalex.org/W2078528584","https://openalex.org/W2285420822","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2296167893","https://openalex.org/W2396918387","https://openalex.org/W2399557756","https://openalex.org/W2404019834","https://openalex.org/W2405774341","https://openalex.org/W2795050058","https://openalex.org/W2798646942","https://openalex.org/W2962866211","https://openalex.org/W2962959469","https://openalex.org/W6629014544","https://openalex.org/W6668948836","https://openalex.org/W6712395177","https://openalex.org/W6712706723","https://openalex.org/W6712950515","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W284174822","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"There":[0],"are":[1,53,106,178,197],"two":[2],"effective":[3],"approaches":[4],"to":[5,166,187,202],"improve":[6,91,213],"the":[7,15,24,28,31,35,39,47,60,69,72,85,92,126,139,154,192,204,209,214],"performance":[8,93],"of":[9,71,94,194],"an":[10],"automatic":[11,48],"speech":[12,49,96,196],"recognizer":[13,97],"with":[14,27,38,119,185],"front-end":[16,40,61,127,168,210],"processing":[17,41,62,88,128,211],"under":[18,219],"noisy":[19,195],"condition,":[20],"one":[21],"is":[22,33],"retraining":[23,73,99],"acoustic":[25,36],"model":[26,37],"enhanced":[29],"features,":[30],"other":[32],"joint-training":[34,75],"model.":[42],"However,":[43],"in":[44,56,68,108,163,176],"real":[45],"life,":[46],"recognition":[50],"(ASR)":[51],"systems":[52],"always":[54],"located":[55],"cloud":[57],"servers":[58],"but":[59],"models":[63],"run":[64],"locally,":[65],"which":[66],"results":[67],"impracticality":[70],"and":[74,100,123,132,145,199,222],"strategy":[76],"for":[77,138],"ASR.":[78],"In":[79,190],"this":[80],"paper,":[81],"we":[82,158],"investigate":[83],"whether":[84],"independent":[86],"frontend":[87],"can":[89,129,212],"directly":[90],"a":[95],"without":[98],"joint-training.":[101],"Three":[102],"common-used":[103],"enhancement":[104,124],"methods":[105,162,184],"evaluated":[107],"different":[109],"time-frequency":[110],"(T-F)":[111],"domains.":[112],"Our":[113],"experiments":[114],"on":[115],"CHiME-3":[116],"reveal":[117],"that,":[118],"appropriate":[120],"T-F":[121],"domains":[122],"methods,":[125,175],"make":[130],"35.30%":[131],"11.78%":[133],"relative":[134],"word-error-rate":[135],"(WER)":[136],"reduction":[137],"Gaussian":[140],"Mixed":[141],"Model":[142],"based":[143,149,174,183],"(GMM-based)":[144],"Deep":[146],"Neural":[147],"Network":[148],"(DNN-based)":[150],"recognizer,":[151],"respectively.":[152],"For":[153,206],"DNN-based":[155],"ASR":[156,217],"system,":[157],"propose":[159],"using":[160],"masking-based":[161],"log-fbank":[164],"domain":[165],"do":[167],"processing.":[169],"We":[170],"find":[171],"that":[172],"masking":[173],"general,":[177],"better":[179],"than":[180],"spectral":[181],"mapping":[182],"respect":[186],"WER":[188],"reduction.":[189],"addition,":[191],"phases":[193],"useless":[198],"even":[200],"harmful":[201],"reduce":[203],"WER.":[205],"generalization":[207],"capability,":[208],"multi-conditional":[215],"trained":[216],"system":[218],"both":[220],"matched":[221],"unmatched":[223],"noise":[224],"condition.":[225]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}