{"id":"https://openalex.org/W4405441041","doi":"https://doi.org/10.1109/wocc61718.2024.10786031","title":"Group-and-Conquer for Multi-Speaker Single-Channel Speech Separation","display_name":"Group-and-Conquer for Multi-Speaker Single-Channel Speech Separation","publication_year":2024,"publication_date":"2024-10-25","ids":{"openalex":"https://openalex.org/W4405441041","doi":"https://doi.org/10.1109/wocc61718.2024.10786031"},"language":"en","primary_location":{"id":"doi:10.1109/wocc61718.2024.10786031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wocc61718.2024.10786031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd Wireless and Optical Communications Conference (WOCC)","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/A5013754167","display_name":"Ya-Fan Yen","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ya-Fan Yen","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Electronics and Electrical Engineering,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Electronics and Electrical Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040050806","display_name":"Hong-Han Shuai","orcid":"https://orcid.org/0000-0003-2216-077X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Han Shuai","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Electronics and Electrical Engineering,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Electronics and Electrical Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013754167"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26250134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"165","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.989300012588501,"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":0.989300012588501,"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":0.9886999726295471,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9125999808311462,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.7774945497512817},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6849240064620972},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5854541659355164},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5648623108863831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5416292548179626},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5230109095573425},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1990031898021698},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12410828471183777},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05823671817779541},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.05362337827682495}],"concepts":[{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.7774945497512817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6849240064620972},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5854541659355164},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5648623108863831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5416292548179626},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5230109095573425},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1990031898021698},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12410828471183777},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05823671817779541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.05362337827682495},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wocc61718.2024.10786031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wocc61718.2024.10786031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd Wireless and Optical Communications Conference (WOCC)","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":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1520930749","https://openalex.org/W1600918697","https://openalex.org/W2006121561","https://openalex.org/W2113242816","https://openalex.org/W2136132422","https://openalex.org/W2141998673","https://openalex.org/W2172256532","https://openalex.org/W2194775991","https://openalex.org/W2295598076","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2971417062","https://openalex.org/W2972513594","https://openalex.org/W3004230583","https://openalex.org/W3011424113","https://openalex.org/W3015199127","https://openalex.org/W3097653961","https://openalex.org/W3197823486","https://openalex.org/W4289665794","https://openalex.org/W4293363567","https://openalex.org/W4297841846","https://openalex.org/W6774995033"],"related_works":["https://openalex.org/W2352794675","https://openalex.org/W1539994214","https://openalex.org/W2051228988","https://openalex.org/W4247094814","https://openalex.org/W108531593","https://openalex.org/W2111712077","https://openalex.org/W8810113","https://openalex.org/W2158636562","https://openalex.org/W2162911572","https://openalex.org/W2791440692"],"abstract_inverted_index":{"We":[0],"propose":[1,22],"to":[2,26,47,56,131],"reduce":[3],"the":[4,9,18,28,35,57,67,77,84,93,98,105,113,117,124,134,137,146],"difficulty":[5],"level":[6],"by":[7,149],"separating":[8],"separation":[10,45,74,80,100,125],"process":[11],"in":[12,17,153],"a":[13,23,43,49,63,72],"group-and-conquer":[14],"way.":[15],"Specifically,":[16],"first":[19],"stage,":[20,115],"we":[21,41],"prediction":[24],"model":[25,46,81,101,126],"estimate":[27],"optimal":[29],"number":[30,58,95],"of":[31,59,87,96],"groups":[32,54],"based":[33],"on":[34,128],"input":[36,106],"mixed":[37,50],"signal.":[38],"In":[39,112],"addition,":[40],"train":[42],"group":[44,73,79,99,118],"separate":[48,104,133],"signal":[51,108],"into":[52,109],"multiple":[53],"according":[55],"groups.":[60,111],"By":[61],"training":[62],"vocal":[64],"network":[65,75],"with":[66,119],"triplet":[68],"cosine":[69],"loss":[70],"and":[71],"simultaneously,":[76],"proposed":[78],"better":[82,132],"learns":[83],"latent":[85],"feature":[86],"each":[88],"group.":[89,138],"As":[90],"such,":[91],"given":[92],"predicted":[94],"groups,":[97],"can":[102],"automatically":[103],"audio":[107],"several":[110],"second":[114],"for":[116],"more":[120],"than":[121],"one":[122],"speaker,":[123],"focuses":[127],"fine-grained":[129],"information":[130],"speech":[135],"among":[136],"Experimental":[139],"results":[140],"show":[141],"that":[142],"our":[143],"approach":[144],"outperforms":[145],"state-of-the-art":[147],"models":[148],"at":[150],"least":[151],"8.68%":[152],"SI-SNRi.":[154]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}