{"id":"https://openalex.org/W4389474630","doi":"https://doi.org/10.1109/mmsp59012.2023.10337699","title":"A Voice-Activity-Aware Loss Function for Continuous Speech Separation","display_name":"A Voice-Activity-Aware Loss Function for Continuous Speech Separation","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4389474630","doi":"https://doi.org/10.1109/mmsp59012.2023.10337699"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp59012.2023.10337699","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mmsp59012.2023.10337699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","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/A5056277765","display_name":"Conggui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Conggui Liu","raw_affiliation_strings":["Fairy Devices Inc.,Tokyo,Japan","Fairy Devices Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Fairy Devices Inc.,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Fairy Devices Inc., Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102251493","display_name":"Yoshinao Sato","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshinao Sato","raw_affiliation_strings":["Fairy Devices Inc.,Tokyo,Japan","Fairy Devices Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Fairy Devices Inc.,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Fairy Devices Inc., Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056277765"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18097027,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9990000128746033,"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/speech-recognition","display_name":"Speech recognition","score":0.688440203666687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6819849610328674},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5458978414535522},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5296304821968079},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5280531048774719},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5010673999786377},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41711288690567017},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4109758138656616},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32818323373794556},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27369797229766846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25451475381851196},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20665502548217773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17205291986465454}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.688440203666687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819849610328674},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5458978414535522},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5296304821968079},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5280531048774719},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5010673999786377},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41711288690567017},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4109758138656616},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32818323373794556},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27369797229766846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25451475381851196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20665502548217773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17205291986465454},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp59012.2023.10337699","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mmsp59012.2023.10337699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","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":24,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W2117678320","https://openalex.org/W2219249508","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2889503488","https://openalex.org/W2952218014","https://openalex.org/W2972693890","https://openalex.org/W3011475224","https://openalex.org/W3015843733","https://openalex.org/W3016232124","https://openalex.org/W3099330747","https://openalex.org/W3133848124","https://openalex.org/W3160071434","https://openalex.org/W3161934504","https://openalex.org/W3162863443","https://openalex.org/W3163842642","https://openalex.org/W3187990717","https://openalex.org/W3195010976","https://openalex.org/W3198575250","https://openalex.org/W4241279559","https://openalex.org/W4245692952","https://openalex.org/W6688816777","https://openalex.org/W6797887590"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2851491717","https://openalex.org/W2089240210"],"abstract_inverted_index":{"Continuous":[0],"speech":[1,13,56,80,111],"separation":[2],"(CSS)":[3],"is":[4,31,37],"gaining":[5],"popularity":[6],"as":[7],"a":[8,47],"realistic":[9],"scenario":[10],"in":[11,82,119],"which":[12,30],"utterances":[14],"partially":[15],"overlap.":[16],"Most":[17],"previous":[18],"studies":[19],"on":[20,77],"CSS":[21],"employed":[22],"the":[23,34,71,91,96,105],"conventional":[24,97],"scale-invariant":[25],"signal-to-noise":[26],"ratio":[27],"(SI-SNR)":[28],"loss,":[29],"ill-defined":[32],"when":[33],"reference":[35],"audio":[36],"silent":[38],"and":[39,58,69,84,113],"thus":[40],"requires":[41],"some":[42],"modifications.":[43],"Hence,":[44],"we":[45],"propose":[46],"voice-activity-aware":[48],"loss":[49,54,63,93,98,107],"function":[50,94,108],"that":[51,90,104],"combines":[52],"SI-SNR":[53],"for":[55,64],"segments":[57],"logarithmic":[59],"root":[60],"mean":[61],"square":[62],"nonspeech":[65,120],"segments.":[66,121],"We":[67],"trained":[68],"evaluated":[70],"block-online":[72],"temporal":[73],"convolutional":[74],"network":[75],"models":[76],"synthetic":[78],"single-channel":[79],"mixtures":[81],"noisy":[83],"reverberant":[85],"environments.":[86],"The":[87],"results":[88],"demonstrated":[89],"proposed":[92,106],"outperformed":[95],"function.":[99],"Furthermore,":[100],"qualitative":[101],"analyses":[102],"indicated":[103],"accurately":[109],"detected":[110],"onsets":[112],"offsets,":[114],"yielding":[115],"reduced":[116],"residual":[117],"noise":[118]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}