{"id":"https://openalex.org/W2939690918","doi":"https://doi.org/10.1109/icassp.2019.8682273","title":"Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches","display_name":"Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939690918","doi":"https://doi.org/10.1109/icassp.2019.8682273","mag":"2939690918"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Hitachi Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Hitachi Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084590882","display_name":"Rintaro Ikeshita","orcid":"https://orcid.org/0000-0003-2608-1999"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rintaro Ikeshita","raw_affiliation_strings":["Hitachi Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076987349","display_name":"Kenji Nagamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Nagamatsu","raw_affiliation_strings":["Hitachi Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9204,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96439694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6630","last_page":"6634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9988999962806702,"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":0.773036003112793},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.7428126931190491},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7295850515365601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.717373788356781},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5589731335639954},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.510767936706543},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47375375032424927},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46545130014419556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3838052749633789},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22236061096191406},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16385790705680847},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08053535223007202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773036003112793},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7428126931190491},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7295850515365601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.717373788356781},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5589731335639954},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.510767936706543},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47375375032424927},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46545130014419556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3838052749633789},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22236061096191406},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16385790705680847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08053535223007202},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1987238397","https://openalex.org/W1989674786","https://openalex.org/W2079623482","https://openalex.org/W2099621636","https://openalex.org/W2103088716","https://openalex.org/W2125336414","https://openalex.org/W2131342762","https://openalex.org/W2147768505","https://openalex.org/W2148613904","https://openalex.org/W2160815625","https://openalex.org/W2164502538","https://openalex.org/W2193413348","https://openalex.org/W2221409856","https://openalex.org/W2296073425","https://openalex.org/W2394932179","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2460742184","https://openalex.org/W2514741789","https://openalex.org/W2517616541","https://openalex.org/W2533523411","https://openalex.org/W2589857635","https://openalex.org/W2696967604","https://openalex.org/W2729190387","https://openalex.org/W2749475572","https://openalex.org/W2749510669","https://openalex.org/W2749980185","https://openalex.org/W2787290364","https://openalex.org/W2796868621","https://openalex.org/W2884797218","https://openalex.org/W2888909726","https://openalex.org/W2889503488","https://openalex.org/W2891405874","https://openalex.org/W2891609809","https://openalex.org/W2891833136","https://openalex.org/W2900440209","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2963266252","https://openalex.org/W6631362777","https://openalex.org/W6647485478","https://openalex.org/W6675409298","https://openalex.org/W6678809451","https://openalex.org/W6687566353","https://openalex.org/W6688843265","https://openalex.org/W6712930963","https://openalex.org/W6713762819","https://openalex.org/W6728841359","https://openalex.org/W6735168207"],"related_works":["https://openalex.org/W2944691285","https://openalex.org/W3081187864","https://openalex.org/W151018310","https://openalex.org/W4380605396","https://openalex.org/W2584084702","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W3012383599","https://openalex.org/W4385611764","https://openalex.org/W172230311"],"abstract_inverted_index":{"This":[0],"paper":[1,92],"presents":[2],"a":[3,23,30,41,54,124,135],"novel":[4],"heterogeneous-input":[5],"multi-channel":[6,15,31,44],"acoustic":[7],"model":[8,48],"(AM)":[9],"that":[10,81,97],"has":[11],"both":[12,146],"single-channel":[13,24,38],"and":[14,68,90,111,134],"input":[16,45],"branches.":[17],"In":[18],"our":[19,113,159],"proposed":[20],"training":[21],"pipeline,":[22],"AM":[25,32,39,67,122],"is":[26,33],"trained":[27,34,66],"first,":[28],"then":[29],"starting":[35],"from":[36],"the":[37,51,62,74,77,83,87,105,117,131,139,143,150,156],"with":[40,116],"randomly":[42],"initialized":[43],"branch.":[46],"Our":[47,71,121],"uniquely":[49],"uses":[50],"power":[52,63],"of":[53,64,147,158],"complemen-tal":[55],"speech":[56],"enhancement":[57],"(SE)":[58],"module":[59],"while":[60],"exploiting":[61],"jointly":[65],"SE":[69],"architecture.":[70],"method":[72],"was":[73],"foundation":[75],"for":[76,130,138,142],"Hitachi/JHU":[78],"CHiME-5":[79,88],"system":[80],"achieved":[82,123],"second-best":[84],"result":[85],"in":[86],"competition,":[89],"this":[91],"details":[93],"various":[94],"investigation":[95],"results":[96,152],"we":[98],"were":[99],"not":[100],"able":[101],"to":[102,155],"present":[103],"during":[104],"competition":[106],"period.":[107],"We":[108],"also":[109],"evaluated":[110],"reconfirmed":[112],"method's":[114],"effectiveness":[115],"AMI":[118,144],"Meeting":[119],"Corpus.":[120],"30.12%":[125],"word":[126],"error":[127],"rate":[128],"(WER)":[129],"development":[132],"set":[133,141],"32.33%":[136],"WER":[137],"evaluation":[140],"Corpus,":[145],"which":[148],"are":[149],"best":[151,157],"ever":[153],"reported":[154],"knowledge.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}