{"id":"https://openalex.org/W1554094125","doi":"https://doi.org/10.1109/icassp.2015.7177969","title":"A pairwise algorithm for pitch estimation and speech separation using deep stacking network","display_name":"A pairwise algorithm for pitch estimation and speech separation using deep stacking network","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1554094125","doi":"https://doi.org/10.1109/icassp.2015.7177969","mag":"1554094125"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7177969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100685577","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-1370-1848"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Computer Science Department, Inner Mongolia University, Hohhot, China","Computer Science Department, Inner Mongolia University, Hohhot, China, 010021"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Computer Science Department, Inner Mongolia University, Hohhot, China, 010021","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Computer Science Department, Inner Mongolia University, Hohhot, China","Computer Science Department, Inner Mongolia University, Hohhot, China, 010021"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Computer Science Department, Inner Mongolia University, Hohhot, China, 010021","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068044387","display_name":"Shuai Nie","orcid":"https://orcid.org/0000-0002-8078-6829"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Nie","raw_affiliation_strings":["National Laboratory of Patten Recognition (NLPR), Institute of Automation, University of Chinese Academy of Sciences, Beijing, China","National Laboratory of Patten Recognition (NLPR), Institute of Automation, University of Chinese Academy of Sciences, Beijing, China, 100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Patten Recognition (NLPR), Institute of Automation, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Patten Recognition (NLPR), Institute of Automation, University of Chinese Academy of Sciences, Beijing, China, 100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]},{"id":"https://openalex.org/I64222039","display_name":"National University of Mongolia","ror":"https://ror.org/04855bv47","country_code":"MN","type":"education","lineage":["https://openalex.org/I64222039"]}],"countries":["CN","MN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Computer Science Department, Inner Mongolia University, Hohhot, Inner Mongolia, CN","Computer Science Department, Inner Mongolia University, Hohhot, China, 010021"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Inner Mongolia University, Hohhot, Inner Mongolia, CN","institution_ids":["https://openalex.org/I2722730","https://openalex.org/I64222039"]},{"raw_affiliation_string":"Computer Science Department, Inner Mongolia University, Hohhot, China, 010021","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039635290","display_name":"Wenju Liu","orcid":"https://orcid.org/0000-0001-9088-8282"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenju Liu","raw_affiliation_strings":["National Laboratory of Patten Recognition (NLPR), Institute of Automation, University of Chinese Academy of Sciences, Beijing, Beijing, CN","National Laboratory of Patten Recognition (NLPR), Institute of Automation, University of Chinese Academy of Sciences, Beijing, China, 100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Patten Recognition (NLPR), Institute of Automation, University of Chinese Academy of Sciences, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Patten Recognition (NLPR), Institute of Automation, University of Chinese Academy of Sciences, Beijing, China, 100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9986000061035156,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.749699056148529},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.6432358026504517},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6329295635223389},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5703420639038086},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5266000032424927},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5265498757362366},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5073663592338562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.507012128829956},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.460495263338089},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4571343660354614},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3735990524291992},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36408090591430664},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3459742069244385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1368650496006012},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12469467520713806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.749699056148529},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.6432358026504517},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6329295635223389},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5703420639038086},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5265498757362366},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5073663592338562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.507012128829956},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.460495263338089},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4571343660354614},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3735990524291992},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36408090591430664},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3459742069244385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1368650496006012},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12469467520713806},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7177969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":19,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1875231349","https://openalex.org/W1888374534","https://openalex.org/W1967590528","https://openalex.org/W1982599741","https://openalex.org/W1990449877","https://openalex.org/W2015469795","https://openalex.org/W2072184010","https://openalex.org/W2097191389","https://openalex.org/W2115129089","https://openalex.org/W2122982914","https://openalex.org/W2149425615","https://openalex.org/W2149600041","https://openalex.org/W2150866759","https://openalex.org/W2152708632","https://openalex.org/W2159202424","https://openalex.org/W2166018245","https://openalex.org/W6639350448","https://openalex.org/W6683207941"],"related_works":["https://openalex.org/W2149528081","https://openalex.org/W2349264490","https://openalex.org/W2052467030","https://openalex.org/W2782776162","https://openalex.org/W109400173","https://openalex.org/W2121987127","https://openalex.org/W141368541","https://openalex.org/W2042145419","https://openalex.org/W2586267569","https://openalex.org/W2367313066"],"abstract_inverted_index":{"Pitch":[0],"information":[1],"is":[2,15,42,70,105,122],"an":[3,66,100],"important":[4],"cue":[5],"for":[6],"speech":[7,22],"separation.":[8,23],"However,":[9],"pitch":[10],"estimation":[11],"in":[12,58,125,157],"noisy":[13],"condition":[14],"also":[16],"a":[17,29,51],"task":[18],"as":[19,21,72],"challenging":[20],"In":[24,62,93],"this":[25],"paper,":[26],"we":[27,111,128],"propose":[28],"supervised":[30],"learning":[31],"architecture":[32],"which":[33,49,86,104],"combines":[34],"these":[35],"two":[36],"problems":[37],"concisely.":[38],"The":[39,74],"proposed":[40,145],"algorithm":[41],"based":[43],"on":[44],"deep":[45,60],"stacking":[46,54],"network":[47],"(DSN)":[48],"provides":[50,99],"method":[52],"of":[53,80,88,138],"simple":[55],"processing":[56],"modules":[57],"building":[59],"architecture.":[61],"the":[63,78,94,113,117,130,135,144],"training":[64],"stage,":[65,96],"ideal":[67],"binary":[68,102,151],"mask":[69,103,152],"used":[71],"target.":[73],"input":[75],"vector":[76],"includes":[77],"outputs":[79],"lower":[81],"module":[82,98,137],"and":[83,90,127,153],"frame-level":[84],"features":[85,115],"consist":[87],"spectral":[89],"pitch-based":[91,114],"features.":[92],"testing":[95],"each":[97],"estimated":[101,150],"employed":[106],"to":[107,116],"re-estimate":[108],"pitch.":[109],"Then":[110],"update":[112],"next":[118],"module.":[119],"This":[120],"procedure":[121],"embedded":[123],"iteratively":[124],"DSN,":[126],"obtain":[129],"final":[131],"separation":[132],"results":[133],"from":[134],"last":[136],"DSN.":[139],"Systematic":[140],"evaluations":[141],"show":[142],"that":[143],"approach":[146],"produces":[147],"high":[148],"quality":[149],"outperforms":[154],"recent":[155],"systems":[156],"generalization.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}