{"id":"https://openalex.org/W3210450519","doi":"https://doi.org/10.21437/interspeech.2022-10406","title":"Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model","display_name":"Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3210450519","doi":"https://doi.org/10.21437/interspeech.2022-10406","mag":"3210450519"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10406","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10406","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5031960713","display_name":"Martin Kocour","orcid":"https://orcid.org/0000-0003-4924-5124"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Martin Kocour","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067790073","display_name":"Kate\u0159ina \u017dmol\u00edkov\u00e1","orcid":"https://orcid.org/0000-0003-4438-8580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katerina Zmolikova","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lucas Ondel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas Ondel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072542443","display_name":"J\u00e1n \u0160vec","orcid":"https://orcid.org/0000-0001-8362-5927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Svec","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5031960713"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1047,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22918323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4955","last_page":"4959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9424999952316284,"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":0.9424999952316284,"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":0.010900000110268593,"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/T10320","display_name":"Neural Networks and Applications","score":0.004000000189989805,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7448463439941406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7277836799621582},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6984395384788513},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6775838136672974},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5161765217781067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3890898823738098},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2998214364051819},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08058679103851318},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0736401379108429}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7448463439941406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277836799621582},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6984395384788513},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6775838136672974},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5161765217781067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3890898823738098},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2998214364051819},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08058679103851318},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0736401379108429},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10406","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10406","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1528056001","https://openalex.org/W1989954041","https://openalex.org/W2060822897","https://openalex.org/W2079362249","https://openalex.org/W2098387242","https://openalex.org/W2101045344","https://openalex.org/W2112921197","https://openalex.org/W2120575449","https://openalex.org/W2144271355","https://openalex.org/W2144763279","https://openalex.org/W2152131029","https://openalex.org/W2160815625","https://openalex.org/W2221409856","https://openalex.org/W2402146185","https://openalex.org/W2734774145","https://openalex.org/W2884797218","https://openalex.org/W2889144942","https://openalex.org/W2900440209","https://openalex.org/W2963843276","https://openalex.org/W2970971581","https://openalex.org/W3020336359","https://openalex.org/W3216221729"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W2533508831","https://openalex.org/W4383605217","https://openalex.org/W2742699532","https://openalex.org/W4281389974","https://openalex.org/W1911859126","https://openalex.org/W2158598479","https://openalex.org/W1964178275","https://openalex.org/W2325482719"],"abstract_inverted_index":{"In":[0,35,121],"typical":[1],"multi-talker":[2,117],"speech":[3,82,118],"recognition":[4,119],"systems,":[5],"a":[6,23,42,48,89,159],"neural":[7],"network-based":[8],"acoustic":[9,59,131],"model":[10,60,132],"predicts":[11],"senone":[12],"state":[13,64],"posteriors":[14,65],"for":[15,66],"each":[16,30],"speaker.":[17],"These":[18],"are":[19],"later":[20],"used":[21,110],"by":[22],"single-talker":[24],"decoder":[25,91],"which":[26,135],"is":[27,44],"applied":[28],"on":[29,158],"speaker-specific":[31],"output":[32],"stream":[33],"separately.":[34],"this":[36,97],"work,":[37],"we":[38,106,127],"argue":[39],"that":[40,51,92],"such":[41],"scheme":[43],"sub-optimal":[45],"and":[46,140],"propose":[47],"principled":[49],"solution":[50],"decodes":[52],"all":[53,67],"speakers":[54],"jointly.":[55],"We":[56,87,146],"modify":[57],"the":[58,70,76,81,85,129,144,148],"to":[61,72,84],"predict":[62],"joint":[63,90,151],"speakers,":[68],"enabling":[69],"network":[71],"express":[73],"uncertainty":[74,98],"about":[75],"attribution":[77],"of":[78,80,96,143,150,155],"parts":[79],"signal":[83],"speakers.":[86],"employ":[88],"can":[93],"make":[94],"use":[95],"together":[99],"with":[100,123,133],"higher-level":[101],"language":[102],"information.":[103],"For":[104],"this,":[105],"revisit":[107],"decoding":[108,152],"algorithms":[109],"in":[111,115,153],"factorial":[112],"generative":[113],"models":[114],"early":[116,125],"systems.":[120],"contrast":[122],"these":[124],"works,":[126],"replace":[128],"GMM":[130],"DNN,":[134],"provides":[136],"greater":[137],"modeling":[138],"power":[139],"simplifies":[141],"part":[142],"inference.":[145],"demonstrate":[147],"advantage":[149],"proof":[154],"concept":[156],"experiments":[157],"mixed-TIDIGITS":[160],"dataset.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}