{"id":"https://openalex.org/W4401609017","doi":"https://doi.org/10.1109/icasspw62465.2024.10627638","title":"An Audio-Quality-Based Multi-Strategy Approach For Target Speaker Extraction in the Misp 2023 Challenge","display_name":"An Audio-Quality-Based Multi-Strategy Approach For Target Speaker Extraction in the Misp 2023 Challenge","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609017","doi":"https://doi.org/10.1109/icasspw62465.2024.10627638"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627638","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627638","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/A5091225905","display_name":"Runduo Han","orcid":"https://orcid.org/0009-0009-4380-4424"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Runduo Han","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001664777","display_name":"Xiaopeng Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Yan","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101155171","display_name":"Weiming Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Xu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032074032","display_name":"Jiayao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayao Sun","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101149305","display_name":"He Wang","orcid":"https://orcid.org/0000-0002-7852-8492"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104212958","display_name":"Quan L\u00fc","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Lu","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd,China"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654008","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0003-4549-6372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd,China"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Software,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5091225905"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65606898,"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":"27","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9904999732971191,"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":0.9904999732971191,"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":0.9891999959945679,"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":0.9677000045776367,"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":0.6613414883613586},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5058695673942566},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.48933476209640503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3270561695098877},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05362382531166077},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.05326840281486511}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6613414883613586},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5058695673942566},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.48933476209640503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3270561695098877},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05362382531166077},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.05326840281486511},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627638","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627638","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2291877678","https://openalex.org/W2891833136","https://openalex.org/W4224919782","https://openalex.org/W4225302959","https://openalex.org/W4372346771","https://openalex.org/W4385823318","https://openalex.org/W4386160029","https://openalex.org/W4392902829"],"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],"describes":[2],"our":[3,26,58],"audio-quality-based":[4],"multi-strategy":[5],"approach":[6,27,59],"for":[7],"the":[8,16,34,48,71,78,82],"audio-visual":[9],"target":[10],"speaker":[11],"extraction":[12,30],"(AVTSE)":[13],"task":[14],"in":[15,81],"Multi-modal":[17],"Information":[18],"based":[19,32],"Speech":[20],"Processing":[21],"(MISP)":[22],"2023":[23],"Challenge.":[24],"Specifically,":[25],"adopts":[28],"different":[29],"strategies":[31],"on":[33,70],"audio":[35],"quality,":[36],"striking":[37],"a":[38,61],"balance":[39],"between":[40],"interference":[41],"removal":[42],"and":[43,68,73],"speech":[44,51],"preservation,":[45],"which":[46],"benifits":[47],"back-end":[49],"automatic":[50],"recognition":[52],"(ASR)":[53],"systems.":[54],"Experiments":[55],"show":[56],"that":[57],"achieves":[60],"character":[62],"error":[63],"rate":[64],"(CER)":[65],"of":[66],"24.2%":[67],"33.2%":[69],"Dev":[72],"Eval":[74],"set,":[75],"respectively,":[76],"obtaining":[77],"second":[79],"place":[80],"challenge.":[83]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
