{"id":"https://openalex.org/W2748820902","doi":"https://doi.org/10.21437/interspeech.2017-579","title":"Joint Training of Multi-Channel-Condition Dereverberation and Acoustic Modeling of Microphone Array Speech for Robust Distant Speech Recognition","display_name":"Joint Training of Multi-Channel-Condition Dereverberation and Acoustic Modeling of Microphone Array Speech for Robust Distant Speech Recognition","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2748820902","doi":"https://doi.org/10.21437/interspeech.2017-579","mag":"2748820902"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-579","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5018911822","display_name":"Fengpei Ge","orcid":"https://orcid.org/0000-0001-5352-1780"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fengpei Ge","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012954193","display_name":"Kehuang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kehuang Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672630","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0002-3126-5103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5018911822"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57379425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3847","last_page":"3851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9966999888420105,"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/joint","display_name":"Joint (building)","score":0.7250611782073975},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7146748900413513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7144328951835632},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5123814344406128},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5024223327636719},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5014491081237793},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4716460108757019},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3464193344116211},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3245922029018402},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10125857591629028},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06369850039482117}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7250611782073975},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7146748900413513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7144328951835632},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5123814344406128},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5024223327636719},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5014491081237793},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4716460108757019},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3464193344116211},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3245922029018402},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10125857591629028},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06369850039482117},{"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-579","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/649496","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/649496","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W258661521","https://openalex.org/W1522199561","https://openalex.org/W1524333225","https://openalex.org/W1598508708","https://openalex.org/W1935589317","https://openalex.org/W1967558850","https://openalex.org/W1973669708","https://openalex.org/W1989314204","https://openalex.org/W1992475611","https://openalex.org/W2044893557","https://openalex.org/W2048142341","https://openalex.org/W2082474452","https://openalex.org/W2107992675","https://openalex.org/W2130722890","https://openalex.org/W2141520175","https://openalex.org/W2153418894","https://openalex.org/W2160373860","https://openalex.org/W2177365772","https://openalex.org/W2183622110","https://openalex.org/W2242685705","https://openalex.org/W2398723458","https://openalex.org/W2402268235","https://openalex.org/W2408713104","https://openalex.org/W2542605056","https://openalex.org/W2606601002","https://openalex.org/W2751679489","https://openalex.org/W3143596294"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2963983801","https://openalex.org/W3119734852"],"abstract_inverted_index":{"We":[0,113],"propose":[1],"a":[2,38,62,106],"novel":[3],"data":[4,50,86,99],"utilization":[5],"strategy,":[6],"called":[7],"multichannel-condition":[8],"learning,":[9],"leveraging":[10],"upon":[11],"complementary":[12],"information":[13],"captured":[14],"in":[15],"microphone":[16],"array":[17],"speech":[18,33,41],"to":[19],"jointly":[20],"train":[21],"dereverberation":[22],"and":[23,88,100],"acoustic":[24],"deep":[25],"neural":[26],"network":[27],"(DNN)":[28],"models":[29],"for":[30,72],"robust":[31],"distant":[32],"recognition.":[34],"Experimental":[35],"results,":[36],"with":[37,101],"single":[39],"automatic":[40],"recognition":[42],"(ASR)":[43],"system,":[44],"on":[45,53,83,96],"the":[46,56],"REVERB2014":[47],"simulated":[48],"evaluation":[49],"show":[51],"that,":[52],"1-channel":[54],"testing,":[55],"baseline":[57],"joint":[58],"training":[59,95],"scheme":[60,79],"attains":[61],"word":[63],"error":[64],"rate":[65],"(WER)":[66],"of":[67,109],"7.47%,":[68],"reduced":[69],"from":[70],"8.72%":[71],"separate":[73],"training.":[74],"The":[75],"proposed":[76],"multi-channel-condition":[77],"learning":[78],"has":[80],"been":[81],"experimented":[82],"different":[84],"channel":[85],"combinations":[87],"usage":[89],"showing":[90],"many":[91],"interesting":[92],"implications.":[93],"Finally,":[94],"all":[97],"8-channel":[98],"DNN-based":[102],"language":[103],"model":[104],"rescoring,":[105],"state-of-the-art":[107],"WER":[108,118],"4.05%":[110],"is":[111],"achieved.":[112],"anticipate":[114],"an":[115],"even":[116],"lower":[117],"when":[119],"combining":[120],"more":[121],"top":[122],"ASR":[123],"systems.":[124]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}