{"id":"https://openalex.org/W2408151586","doi":"https://doi.org/10.21437/interspeech.2015-660","title":"Speaker-dependent multipitch tracking using deep neural networks","display_name":"Speaker-dependent multipitch tracking using deep neural networks","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2408151586","doi":"https://doi.org/10.21437/interspeech.2015-660","mag":"2408151586"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101800003","display_name":"Yuzhou Liu","orcid":"https://orcid.org/0000-0002-7030-9121"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuzhou Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3279","last_page":"3283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.994700014591217,"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":0.994700014591217,"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":0.9940999746322632,"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":0.9934999942779541,"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":0.7092015147209167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.684342086315155},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6073331832885742},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5913105010986328},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5749833583831787},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5518284440040588},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.5508440136909485},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5244712829589844},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.42380407452583313},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4175460934638977},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.416026771068573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40004944801330566},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.364229679107666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10741662979125977},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08348077535629272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092015147209167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.684342086315155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6073331832885742},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5913105010986328},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5749833583831787},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5518284440040588},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.5508440136909485},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5244712829589844},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.42380407452583313},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4175460934638977},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.416026771068573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40004944801330566},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364229679107666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10741662979125977},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08348077535629272},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Multipitch":[0],"tracking":[1],"is":[2,11,65,79],"important":[3],"for":[4,67,81],"speech":[5],"and":[6,22,76,97,119,141],"signal":[7],"processing.":[8],"However,":[9],"it":[10],"challenging":[12],"to":[13,39,106],"design":[14],"an":[15],"algorithm":[16],"that":[17,133],"achieves":[18],"accurate":[19],"pitch":[20,43,117,124],"estimation":[21],"correct":[23],"speaker":[24,69,83,92],"assignment":[25],"at":[26,157],"the":[27,41,72,77,121,134,151,162],"same":[28],"time.":[29],"In":[30],"this":[31],"paper,":[32],"deep":[33],"neural":[34],"networks":[35],"(DNNs)":[36],"are":[37,61,103],"used":[38],"model":[40,113],"probabilistic":[42],"states":[44],"of":[45,55,94,161],"two":[46,53,163],"simultaneous":[47],"speakers.":[48],"To":[49],"capture":[50],"speaker-dependent":[51,142],"information,":[52],"types":[54],"DNN":[56],"with":[57,99,126],"different":[58],"training":[59,98],"strategies":[60],"proposed.":[62],"The":[63],"first":[64],"trained":[66,80],"each":[68,82],"enrolled":[70],"in":[71,165],"system":[73],"(speaker-dependent":[74],"DNN),":[75],"second":[78],"pair":[84],"(speaker-pair-dependent":[85],"DNN).":[86],"Several":[87],"extensions,":[88],"including":[89],"gender-pair-dependent":[90,95],"DNNs,":[91],"adaptation":[93],"DNNs":[96],"multiple":[100],"energy":[101],"ratios,":[102],"introduced":[104],"later":[105],"relax":[107],"constraints.":[108],"A":[109],"factorial":[110],"hidden":[111],"Markov":[112],"(FHMM)":[114],"then":[115],"integrates":[116],"probabilities":[118],"generates":[120],"most":[122],"likely":[123],"tracks":[125],"a":[127,166],"junction":[128],"tree":[129],"algorithm.":[130],"Experiments":[131],"show":[132],"proposed":[135,152],"methods":[136,153],"substantially":[137],"outperform":[138],"other":[139],"speaker-independent":[140],"multipitch":[143],"trackers":[144],"on":[145],"two-speaker":[146],"mixtures.":[147],"With":[148],"multi-ratio":[149],"training,":[150],"achieve":[154],"consistent":[155],"performance":[156],"various":[158],"energies":[159],"ratios":[160],"speakers":[164],"mixture.":[167]},"counts_by_year":[{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}