{"id":"https://openalex.org/W4401611059","doi":"https://doi.org/10.1109/icasspw62465.2024.10626098","title":"ConVoiFilter: A Case Study of Doing Cocktail Party Speech Recognition","display_name":"ConVoiFilter: A Case Study of Doing Cocktail Party Speech Recognition","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401611059","doi":"https://doi.org/10.1109/icasspw62465.2024.10626098"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5044152577","display_name":"Thai Binh Nguyen","orcid":"https://orcid.org/0009-0008-8100-6338"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thai-Binh Nguyen","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023053982","display_name":"Alexander Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Waibel","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.2995,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5096928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"565","last_page":"569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4975000023841858,"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":0.4975000023841858,"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":0.4715000092983246,"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/computer-science","display_name":"Computer science","score":0.636073887348175},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6314378380775452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.636073887348175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6314378380775452}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1786709202","https://openalex.org/W2078298881","https://openalex.org/W2144499799","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2884797218","https://openalex.org/W2891833136","https://openalex.org/W2901243971","https://openalex.org/W2962788625","https://openalex.org/W2962935966","https://openalex.org/W2964238697","https://openalex.org/W2972541922","https://openalex.org/W2973062255","https://openalex.org/W3004597053","https://openalex.org/W3016232124","https://openalex.org/W3086154751","https://openalex.org/W3089512998","https://openalex.org/W3096090308","https://openalex.org/W3097777922","https://openalex.org/W3197479040","https://openalex.org/W4250439258","https://openalex.org/W4281492411","https://openalex.org/W4311000453","https://openalex.org/W6604195100","https://openalex.org/W6688816777","https://openalex.org/W6780218876","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,40],"end-to-end":[4],"model":[5,23,44,89,109],"designed":[6],"to":[7,54,67,99,110],"improve":[8],"automatic":[9],"speech":[10,27,73],"recognition":[11],"(ASR)":[12],"for":[13],"a":[14,18,25,84],"particular":[15],"speaker":[16],"in":[17,69,96,101],"crowded,":[19],"noisy":[20],"environment.":[21],"The":[22,43],"utilizes":[24],"single-channel":[26],"enhancement":[28,74],"module":[29],"that":[30,78],"isolates":[31],"the":[32,88,92],"speaker\u2019s":[33],"voice":[34],"from":[35,52,94],"background":[36],"noise":[37],"(ConVoiFilter)":[38],"and":[39],"ASR":[41,80],"module.":[42],"can":[45,75,90],"decrease":[46,79],"ASR\u2019s":[47],"word":[48],"error":[49],"rate":[50],"(WER)":[51],"80%":[53],"26.4%":[55,95],"through":[56],"this":[57],"approach.":[58],"Typically,":[59],"these":[60],"two":[61],"components":[62],"are":[63],"adjusted":[64],"independently":[65],"due":[66],"variations":[68],"data":[70],"requirements.":[71],"However,":[72],"create":[76],"anomalies":[77],"efficiency.":[81],"By":[82],"implementing":[83],"joint":[85,102],"fine-tuning":[86],"strategy,":[87],"reduce":[91],"WER":[93],"separate":[97],"tuning":[98],"14.5%":[100],"tuning.":[103],"We":[104],"openly":[105],"share":[106],"our":[107],"pre-trained":[108],"foster":[111],"further":[112],"research":[113],"hf.co/nguyenvulebinh/voice-filter.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}