{"id":"https://openalex.org/W4405709776","doi":"https://doi.org/10.1109/iscslp63861.2024.10800151","title":"Insights from Hyperparameter Scaling of Online Speech Separation","display_name":"Insights from Hyperparameter Scaling of Online Speech Separation","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709776","doi":"https://doi.org/10.1109/iscslp63861.2024.10800151"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800151","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":"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/A5100771026","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0003-4095-3503"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100771026"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2706002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"561","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9915000200271606,"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/T11309","display_name":"Music and Audio Processing","score":0.9240999817848206,"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/hyperparameter","display_name":"Hyperparameter","score":0.80262291431427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6899816393852234},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6339043974876404},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5773434042930603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5065320730209351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43398499488830566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3784332871437073},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35585182905197144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12523597478866577}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.80262291431427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899816393852234},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6339043974876404},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5773434042930603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5065320730209351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43398499488830566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3784332871437073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35585182905197144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12523597478866577},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800151","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W3151851237","https://openalex.org/W3163652268","https://openalex.org/W3164605550","https://openalex.org/W3185109982","https://openalex.org/W4224938485","https://openalex.org/W4296068774","https://openalex.org/W4297841651","https://openalex.org/W4372260250","https://openalex.org/W4372260557","https://openalex.org/W4385756463","https://openalex.org/W4385822305","https://openalex.org/W4385822385","https://openalex.org/W4385823327","https://openalex.org/W6631190155","https://openalex.org/W6839101543"],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2140186469","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W2775233965","https://openalex.org/W4318559728","https://openalex.org/W4360995913","https://openalex.org/W4312193868","https://openalex.org/W4308165509"],"abstract_inverted_index":{"With":[0],"the":[1,22,65,87,96,102,125,129,141,144,156,159,166],"rapid":[2],"development":[3],"of":[4,10,98,106,143,146,158],"deep":[5],"learning,":[6],"a":[7],"large":[8],"number":[9,105,145],"models":[11,29,75,168],"with":[12,78,152],"excellent":[13],"performance":[14,62,133],"for":[15,34,52,164],"speech":[16,36,54,116],"separation":[17,37,55,117],"tasks":[18,38],"have":[19,56],"emerged":[20],"in":[21,86],"literature.":[23,88],"Despite":[24],"their":[25,79],"impressive":[26],"performance,":[27,104],"these":[28,74],"usually":[30],"cannot":[31],"be":[32],"used":[33],"online":[35,53,115],"due":[39],"to":[40,59],"high":[41],"computational":[42,109,149],"and":[43,108,120,134,148,169],"memory":[44],"costs.":[45],"In":[46],"recent":[47],"years,":[48],"some":[49],"approaches":[50],"tailored":[51],"been":[57],"developed":[58],"achieve":[60],"state-of-the-art":[61],"while":[63],"keeping":[64],"model":[66,103,132],"lightweight.":[67],"However,":[68],"it":[69],"is":[70],"often":[71],"unclear":[72],"how":[73],"can":[76],"scale":[77],"architecture-specific":[80],"hyperparameters":[81],"as":[82],"they":[83],"are":[84],"under-explored":[85],"To":[89],"fill":[90],"this":[91,93],"gap,":[92],"paper":[94],"investigates":[95],"effect":[97],"hyper-parameter":[99],"scaling":[100,165],"on":[101,112,124,155],"parameters,":[107],"cost":[110],"based":[111],"two":[113,167,171],"representative":[114],"models,":[118],"BSRNN":[119],"SkiM.":[121],"Experimental":[122],"results":[123,157],"Libri2Mix":[126],"dataset":[127],"reveal":[128],"relationship":[130],"between":[131],"composite":[135],"hyperparameter":[136],"configurations.":[137],"We":[138],"also":[139],"derive":[140],"patterns":[142],"parameters":[147],"costs":[150],"varying":[151],"hyperparameters.":[153],"Based":[154],"analysis,":[160],"we":[161],"give":[162],"suggestions":[163],"summarize":[170],"common":[172],"trends.":[173]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}