{"id":"https://openalex.org/W4406858820","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848630","title":"Peer Learning via Shared Speech Representation Prediction for Target Speech Separation","display_name":"Peer Learning via Shared Speech Representation Prediction for Target Speech Separation","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858820","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848630"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5085065604","display_name":"Xusheng Yang","orcid":"https://orcid.org/0000-0002-5421-0316"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xusheng Yang","raw_affiliation_strings":["Peking University,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Peking University,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100962843","display_name":"Zifeng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zifeng Zhao","raw_affiliation_strings":["Peking University,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Peking University,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034401157","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0002-0144-1794"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Peking University,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210128628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085065604"],"corresponding_institution_ids":["https://openalex.org/I4210128628"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2435393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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":0.9839000105857849,"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":0.9258000254631042,"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":0.7407963275909424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6634472608566284},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5044406652450562},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4981963634490967},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4004219174385071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3916863203048706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2349686324596405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407963275909424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6634472608566284},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5044406652450562},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4981963634490967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4004219174385071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3916863203048706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2349686324596405},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":26,"referenced_works":["https://openalex.org/W2170864449","https://openalex.org/W2221409856","https://openalex.org/W2620998106","https://openalex.org/W2939518062","https://openalex.org/W2952218014","https://openalex.org/W3015199127","https://openalex.org/W3015636705","https://openalex.org/W3016257794","https://openalex.org/W3024147341","https://openalex.org/W3097653961","https://openalex.org/W3171007011","https://openalex.org/W3182657421","https://openalex.org/W3206315738","https://openalex.org/W4200634403","https://openalex.org/W4225281800","https://openalex.org/W4281492411","https://openalex.org/W4372347014","https://openalex.org/W4385822256","https://openalex.org/W4385822829","https://openalex.org/W4385823088","https://openalex.org/W4390872668","https://openalex.org/W6638523607","https://openalex.org/W6777776875","https://openalex.org/W6778102432","https://openalex.org/W6790290720","https://openalex.org/W6791742336"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W4308092240","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W4385464961","https://openalex.org/W2060903012","https://openalex.org/W2021161555","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Target":[0],"speech":[1,23,36,95],"separation":[2,120],"approaches":[3],"widely":[4],"use":[5],"the":[6,10,14,20,41,56,87,100,109,115,124,128],"encoder-separation-decoder":[7],"framework.":[8,77],"Generally,":[9],"crucial":[11],"idea":[12],"of":[13,22,83,130],"framework":[15],"is":[16],"how":[17],"to":[18,25,33,48,118],"map":[19],"mixture":[21,58,84],"signals":[24],"a":[26,70,81,93],"distinctive":[27,42],"representation.":[28],"However,":[29],"existing":[30],"methods":[31],"fail":[32],"learn":[34],"discriminative":[35,66,102],"representations":[37],"because":[38],"they":[39],"ignore":[40],"characteristics":[43,64],"(tone":[44],"and":[45,65,91,112],"timbre)":[46],"related":[47],"each":[49],"target":[50,89],"speaker,":[51],"which":[52],"are":[53],"shared":[54,62],"within":[55],"corresponding":[57],"samples.":[59],"To":[60],"acquire":[61],"speaker":[63,90],"representations,":[67],"we":[68,79],"propose":[69],"novel":[71],"\"peer":[72],"learning\"":[73],"method":[74],"for":[75],"this":[76],"Specifically,":[78],"construct":[80],"pair":[82],"samples":[85],"involving":[86],"same":[88],"design":[92],"two-branch":[94],"representation":[96,103],"prediction":[97,116],"module.":[98],"Then,":[99],"more":[101],"can":[104],"be":[105],"determined":[106],"via":[107],"computing":[108],"signal-to-noise":[110],"ratio":[111],"exchanged":[113],"in":[114],"module":[117],"improve":[119],"performance.":[121],"Experiments":[122],"on":[123],"Libri2Mix":[125],"dataset":[126],"demonstrate":[127],"effectiveness":[129],"our":[131],"method.":[132]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}