{"id":"https://openalex.org/W4405709395","doi":"https://doi.org/10.1109/iscslp63861.2024.10800658","title":"Cuside-Array: A Streaming Multi-Channel End-to-End Speech Recognition System with Realistic Evaluations","display_name":"Cuside-Array: A Streaming Multi-Channel End-to-End Speech Recognition System with Realistic Evaluations","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709395","doi":"https://doi.org/10.1109/iscslp63861.2024.10800658"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":null,"display_name":"Xiangzhu Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangzhu Kong","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113291959","display_name":"Tianqi Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianqi Ning","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2623114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"721","last_page":"725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9866999983787537,"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":0.9866999983787537,"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":0.9854000210762024,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8424011468887329},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7365636229515076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6520200967788696},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5199885964393616},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23979294300079346}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8424011468887329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365636229515076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6520200967788696},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5199885964393616},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23979294300079346}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":30,"referenced_works":["https://openalex.org/W1163332818","https://openalex.org/W1932968309","https://openalex.org/W1985368711","https://openalex.org/W2289912446","https://openalex.org/W2329068866","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2400339399","https://openalex.org/W2506203739","https://openalex.org/W2559809918","https://openalex.org/W2640112133","https://openalex.org/W2763188033","https://openalex.org/W2900091068","https://openalex.org/W2913718171","https://openalex.org/W3020336359","https://openalex.org/W3096396467","https://openalex.org/W3169722760","https://openalex.org/W3196117288","https://openalex.org/W3197654132","https://openalex.org/W3207834622","https://openalex.org/W4226071457","https://openalex.org/W4296070361","https://openalex.org/W4319586472","https://openalex.org/W4319862656","https://openalex.org/W4375868938","https://openalex.org/W4385245566","https://openalex.org/W6688816777","https://openalex.org/W6735168207","https://openalex.org/W6780006332","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Recently":[0],"multi-channel":[1],"end-to-end":[2,11],"(ME2E)":[3],"ASR":[4,12,19,53],"systems":[5],"have":[6],"emerged.":[7],"While":[8],"streaming":[9,17,51,85,107],"single-channel":[10,127],"has":[13],"been":[14],"extensively":[15],"studied,":[16],"ME2E":[18,52,81,100,137],"is":[20],"limited":[21],"in":[22,109,122],"exploration.":[23],"Additionally,":[24],"recent":[25,66],"studies":[26],"call":[27],"attention":[28],"to":[29,104,125,129],"the":[30,60,65,76,118],"gap":[31],"between":[32],"in-distribution":[33],"(ID)":[34],"and":[35,39,54,73,90,112,136],"out-of-distribution":[36],"(OOD)":[37],"tests":[38],"doing":[40],"realistic":[41],"evaluations.":[42],"This":[43],"paper":[44],"focuses":[45],"on":[46],"two":[47],"research":[48],"problems:":[49],"realizing":[50],"improving":[55],"OOD":[56,113,131],"generalization.":[57],"We":[58],"propose":[59],"CUSIDE-array":[61,99,121],"method,":[62],"which":[63],"integrates":[64],"CUSIDE":[67],"method-ology":[68],"(Chunking,":[69],"Simulating":[70],"Future":[71],"Context":[72],"Decoding)":[74],"into":[75],"neural":[77],"beamformer":[78],"approach":[79],"of":[80,87,96,120],"ASR.":[82],"It":[83],"enables":[84],"processing":[86],"both":[88,110],"front-end":[89],"back-end":[91,134],"with":[92],"a":[93],"total":[94],"latency":[95],"402ms.":[97],"The":[98],"models":[101],"are":[102],"shown":[103],"achieve":[105],"superior":[106],"results":[108],"ID":[111],"tests.":[114],"Realistic":[115],"evaluations":[116],"confirm":[117],"advantage":[119],"its":[123],"capability":[124],"consume":[126],"data":[128],"improve":[130],"generalization":[132],"via":[133],"pretraining":[135],"fine-tuning.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}