{"id":"https://openalex.org/W4385823366","doi":"https://doi.org/10.21437/interspeech.2023-257","title":"Multi-channel multi-speaker transformer for speech recognition","display_name":"Multi-channel multi-speaker transformer for speech recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823366","doi":"https://doi.org/10.21437/interspeech.2023-257"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-257","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.02688","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102874008","display_name":"Yifan Guo","orcid":"https://orcid.org/0000-0002-5008-2513"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guo Yifan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108578749","display_name":"Tian Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Yao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109630497","display_name":"Hongbin Suo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suo Hongbin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5092639653","display_name":"Wan Yulong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan Yulong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102874008"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2455,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52204134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4918","last_page":"4922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.7656000256538391,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.7656000256538391,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T14438","display_name":"Advanced Scientific Research Methods","score":0.698199987411499,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6399000287055969,"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":0.7044709324836731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6895581483840942},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5906742811203003},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5144434571266174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11005252599716187},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10424220561981201},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07413959503173828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044709324836731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6895581483840942},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5906742811203003},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5144434571266174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11005252599716187},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10424220561981201},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07413959503173828}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-257","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.02688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.02688","pdf_url":"https://arxiv.org/pdf/2601.02688","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.02688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.02688","pdf_url":"https://arxiv.org/pdf/2601.02688","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823366.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"With":[0],"the":[1,29,32,55,64,78,83,86],"development":[2],"of":[3,31,54,110],"teleconferencing":[4],"and":[5,94,105],"in-vehicle":[6],"voice":[7],"assistants,":[8],"far-field":[9,36,70],"multi-speaker":[10,66,71],"speech":[11],"recognition":[12],"has":[13,24],"become":[14],"a":[15,20],"hot":[16],"research":[17],"topic.":[18],"Recently,":[19],"multi-channel":[21,65,95],"transformer":[22,33,67],"(MCT)":[23],"been":[25],"proposed,":[26],"which":[27],"demonstrates":[28],"ability":[30],"to":[34],"model":[35],"acoustic":[37,44],"environments.":[38],"However,":[39],"MCT":[40],"cannot":[41],"encode":[42],"high-dimensional":[43],"features":[45],"for":[46,69],"each":[47],"speaker":[48],"from":[49],"mixed":[50],"input":[51],"audio":[52],"because":[53],"interference":[56],"between":[57],"speakers.":[58],"Based":[59],"on":[60,77],"these,":[61],"we":[62],"propose":[63],"(M2Former)":[68],"ASR":[72],"in":[73,108],"this":[74],"paper.":[75],"Experiments":[76],"SMS-WSJ":[79],"benchmark":[80],"show":[81],"that":[82],"M2Former":[84],"outperforms":[85],"neural":[87],"beamformer,":[88],"MCT,":[89],"dual-path":[90],"RNN":[91],"with":[92],"transform-average-concatenate":[93],"deep":[96],"clustering":[97],"based":[98],"end-to-end":[99],"systems":[100],"by":[101],"9.2%,":[102],"14.3%,":[103],"24.9%,":[104],"52.2%":[106],"respectively,":[107],"terms":[109],"relative":[111],"word":[112],"error":[113],"rate":[114],"reduction.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}