{"id":"https://openalex.org/W3016067707","doi":"https://doi.org/10.1109/icassp40776.2020.9053460","title":"Single-Channel Speech Separation Integrating Pitch Information Based on a Multi Task Learning Framework","display_name":"Single-Channel Speech Separation Integrating Pitch Information Based on a Multi Task Learning Framework","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016067707","doi":"https://doi.org/10.1109/icassp40776.2020.9053460","mag":"3016067707"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5101585451","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-1075-7694"},"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, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012124455","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0002-3758-6493"},"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":"Rui Liu","raw_affiliation_strings":["Department of Machine Intelligence, Speech and Hearing Research Center, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632489","display_name":"Tao Song","orcid":"https://orcid.org/0000-0002-1439-0033"},"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":"Tao Song","raw_affiliation_strings":["Department of Machine Intelligence, Speech and Hearing Research Center, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Speech and Hearing Research Center, 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, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394911","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0002-6640-7140"},"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, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101585451"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51619487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"88","issue":null,"first_page":"7279","last_page":"7283"},"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":0.9994000196456909,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.7300332188606262},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7006460428237915},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6135361790657043},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5784602761268616},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5443690419197083},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4785390794277191},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4711564779281616},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4308609366416931},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.4201866686344147},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41763585805892944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41587546467781067},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4120640754699707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2710464596748352},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0843135416507721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300332188606262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7006460428237915},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6135361790657043},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5784602761268616},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5443690419197083},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4785390794277191},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4711564779281616},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4308609366416931},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.4201866686344147},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41763585805892944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41587546467781067},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4120640754699707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2710464596748352},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0843135416507721},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/5","score":0.5799999833106995,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1554094125","https://openalex.org/W1964538581","https://openalex.org/W2017608047","https://openalex.org/W2022697906","https://openalex.org/W2025946228","https://openalex.org/W2127851351","https://openalex.org/W2143341575","https://openalex.org/W2166018245","https://openalex.org/W2221409856","https://openalex.org/W2315268655","https://openalex.org/W2734774145","https://openalex.org/W2889992917","https://openalex.org/W2936423518","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963954250"],"related_works":["https://openalex.org/W2149528081","https://openalex.org/W2349264490","https://openalex.org/W2052467030","https://openalex.org/W2782776162","https://openalex.org/W4287694193","https://openalex.org/W3124278207","https://openalex.org/W141368541","https://openalex.org/W2121987127","https://openalex.org/W3046871516","https://openalex.org/W2586267569"],"abstract_inverted_index":{"Pitch":[0],"is":[1],"a":[2,27,68],"critical":[3],"cue":[4],"for":[5,142],"speech":[6,20,35,47,74,132],"separation":[7,48,75,133],"in":[8,18,22,37,66,113,128],"humans'":[9],"auditory":[10],"perception.":[11,39],"Although":[12],"the":[13,83,110,114,119,124],"technology":[14],"of":[15,130],"tracking":[16,51,78],"pitch":[17,32,50,77,135],"single-talker":[19],"succeeds":[21],"many":[23],"applications,":[24],"it's":[25],"still":[26],"challenging":[28,143],"problem":[29],"to":[30,45,53],"extract":[31],"information":[33],"from":[34,57,106],"mixtures":[36],"machine":[38],"In":[40,95],"this":[41],"paper,":[42],"we":[43],"aimed":[44],"combine":[46],"and":[49,76,103,134],"together":[52],"let":[54],"them":[55],"benefit":[56,105],"each":[58,107],"other.":[59],"A":[60],"multi-task":[61,121],"learning":[62],"framework":[63,122],"was":[64,79,139],"proposed,":[65],"which":[67],"unified":[69],"objective":[70],"that":[71],"considered":[72],"both":[73,131],"used,":[80],"based":[81],"on":[82],"utterance-level":[84],"permutation":[85],"invariant":[86],"training":[87],"(uPIT)":[88],"as":[89,91],"well":[90],"deep":[92],"clustering":[93],"(DPCL).":[94],"such":[96],"framework,":[97,127],"two":[98],"tasks":[99],"were":[100],"optimized":[101],"simultaneously":[102],"could":[104],"other":[108],"through":[109],"sharing":[111],"layers":[112],"networks.":[115],"Experimental":[116],"results":[117],"indicated":[118],"proposed":[120],"outperformed":[123],"corresponding":[125],"single-task":[126],"terms":[129],"tracking.":[136],"The":[137],"improvement":[138],"more":[140],"significant":[141],"same-gender":[144],"mixtures.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}