{"id":"https://openalex.org/W2937932858","doi":"https://doi.org/10.1109/icassp.2019.8683850","title":"A Spectral-change-aware Loss Function for DNN-based Speech Separation","display_name":"A Spectral-change-aware Loss Function for DNN-based Speech Separation","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2937932858","doi":"https://doi.org/10.1109/icassp.2019.8683850","mag":"2937932858"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100674281","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-6482-2535"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Department of Machine Intelligence, Speech and Hearing Research Center, and Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Speech and Hearing Research Center, and Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Department of Machine Intelligence, Speech and Hearing Research Center, and Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Speech and Hearing Research Center, and Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394926","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0002-8067-0201"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["Department of Machine Intelligence, Speech and Hearing Research Center, and Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Speech and Hearing Research Center, and Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100674281"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.3317,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.53001105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6870","last_page":"6874"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7802919149398804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.651665985584259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.649564266204834},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6488304138183594},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5921546816825867},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4619176387786865},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.4617353677749634},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42337024211883545},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3371683955192566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33075591921806335},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2797076106071472},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1470579206943512},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1212863028049469}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7802919149398804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.651665985584259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.649564266204834},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6488304138183594},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5921546816825867},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4619176387786865},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.4617353677749634},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42337024211883545},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3371683955192566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33075591921806335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2797076106071472},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1470579206943512},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1212863028049469},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W10681493","https://openalex.org/W160800111","https://openalex.org/W190004713","https://openalex.org/W258847520","https://openalex.org/W1963969987","https://openalex.org/W1963970749","https://openalex.org/W1974387177","https://openalex.org/W1989039956","https://openalex.org/W2009348408","https://openalex.org/W2017608047","https://openalex.org/W2030909238","https://openalex.org/W2045691673","https://openalex.org/W2057200980","https://openalex.org/W2060237776","https://openalex.org/W2072720341","https://openalex.org/W2085191029","https://openalex.org/W2086139506","https://openalex.org/W2141998673","https://openalex.org/W2789063613","https://openalex.org/W4231807801","https://openalex.org/W4243882841","https://openalex.org/W4245838404","https://openalex.org/W4385245566","https://openalex.org/W6600432655","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2361247493","https://openalex.org/W2157330024","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W2952979007","https://openalex.org/W1998374630","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Speech":[0],"separation":[1,54,119],"can":[2,26],"be":[3,27],"treated":[4],"as":[5],"a":[6,23,35,82],"mask":[7,33,124],"estimation":[8,125],"problem":[9],"where":[10,67,86],"supervised":[11],"learning":[12,50],"is":[13,74],"employed":[14],"to":[15,22,56,103],"construct":[16],"the":[17,31,58,64,68,89,104,141,148,160],"mapping":[18],"from":[19,70,88],"acoustic":[20],"features":[21],"mask.":[24,168],"Interference":[25],"reduced":[28],"by":[29],"applying":[30],"estimated":[32,167],"on":[34,117],"time-frequency":[36],"(T-F)":[37],"representation":[38,73],"of":[39,48,123,134,155,162,166],"noisy":[40],"speech,":[41],"resulting":[42],"in":[43,121,159],"improved":[44],"speech":[45,53,118,149],"intelligibility.":[46],"Most":[47],"existing":[49],"networks":[51],"for":[52],"aim":[55],"minimize":[57],"Mean":[59],"Square":[60],"Error":[61],"(MSE)":[62],"over":[63,96],"training":[65],"set,":[66],"loss":[69,84,87,113,143],"each":[71],"T-F":[72,90,105],"equally":[75],"weighted.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"proposed":[81,142],"spectral-change-aware":[83,112],"function,":[85],"units":[91,106],"with":[92,107],"large":[93],"spectral":[94,109],"changes":[95],"time":[97],"were":[98],"assigned":[99],"higher":[100],"weights":[101],"compared":[102],"minor":[108],"changes.":[110],"Such":[111],"function":[114,144],"was":[115],"evaluated":[116],"performance":[120],"terms":[122],"accuracy,":[126],"short-time":[127],"objective":[128],"intelligibility":[129,150],"(STOI)":[130],"and":[131,151],"SNR":[132,153],"gain":[133,154],"unvoiced":[135,156],"segments.":[136],"The":[137],"results":[138],"indicated":[139],"that":[140],"could":[145],"further":[146],"improve":[147],"increase":[152],"segments":[157],"even":[158],"cost":[161],"increased":[163],"error":[164],"rate":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}