{"id":"https://openalex.org/W2635922319","doi":"https://doi.org/10.1109/icassp.2017.7952173","title":"A novel pitch extraction based on jointly trained deep BLSTM Recurrent Neural Networks with bottleneck features","display_name":"A novel pitch extraction based on jointly trained deep BLSTM Recurrent Neural Networks with bottleneck features","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2635922319","doi":"https://doi.org/10.1109/icassp.2017.7952173","mag":"2635922319"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5100395443","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0001-8800-7239"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379743","display_name":"Dawei Zhang","orcid":"https://orcid.org/0000-0002-0841-7826"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101398585","display_name":"Yibin Zheng","orcid":"https://orcid.org/0000-0001-9158-1813"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":1.573,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85938122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"336","last_page":"340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9958999752998352,"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":0.8437914848327637},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7286666631698608},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6804331541061401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6674622893333435},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6204853057861328},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5774532556533813},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5638880729675293},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48722043633461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48362627625465393},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.453946590423584},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42335885763168335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8437914848327637},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7286666631698608},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6804331541061401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6674622893333435},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6204853057861328},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5774532556533813},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5638880729675293},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48722043633461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48362627625465393},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.453946590423584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42335885763168335},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/icassp.2017.7952173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1528954144","https://openalex.org/W1598508708","https://openalex.org/W1974387177","https://openalex.org/W1990449877","https://openalex.org/W1993064527","https://openalex.org/W1995966271","https://openalex.org/W2013712815","https://openalex.org/W2015143272","https://openalex.org/W2042141988","https://openalex.org/W2052252043","https://openalex.org/W2055911634","https://openalex.org/W2085191029","https://openalex.org/W2091425152","https://openalex.org/W2115129089","https://openalex.org/W2119599673","https://openalex.org/W2130086727","https://openalex.org/W2141125852","https://openalex.org/W2151251521","https://openalex.org/W2153181479","https://openalex.org/W2172485033","https://openalex.org/W2185814970","https://openalex.org/W2294797155","https://openalex.org/W2396495723","https://openalex.org/W2403004229","https://openalex.org/W2406544397","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W3013299381"],"abstract_inverted_index":{"Pitch":[0],"is":[1,8,15,46,60,95],"an":[2],"important":[3],"characteristic":[4],"of":[5,103],"speech":[6,54],"and":[7,101,132,141],"useful":[9],"for":[10,116],"many":[11],"applications.":[12],"However,":[13],"it":[14],"still":[16],"challenging":[17],"to":[18,33,48,52,86,110,138],"estimate":[19,87],"pitch":[20,58,88,117,130,152],"in":[21],"strong":[22],"noise.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"propose":[28,109],"a":[29,37,62,72],"joint":[30],"training":[31],"approach":[32,146],"determinate":[34],"pitch.":[35],"First,":[36],"Bidirectional":[38],"Long":[39],"Short-Term":[40],"Memory":[41],"Recurrent":[42],"Neural":[43],"Networks":[44],"(BLSTMRNN)":[45],"trained":[47,96],"map":[49],"the":[50,57,80,90,124],"noisy":[51,142],"clean":[53,81],"features.":[55],"Second,":[56],"estimation":[59,131,153],"also":[61,108,147],"BLSTM-RNN":[63,94],"model.":[64],"The":[65,119,144],"feature":[66],"mapping":[67],"neural":[68,92],"network":[69],"serves":[70],"as":[71],"noise":[73],"normalization":[74],"module":[75],"aiming":[76],"at":[77],"explicitly":[78],"generating":[79],"features":[82,100,115],"which":[83],"are":[84],"easier":[85],"by":[89],"following":[91],"network.":[93],"on":[97],"sequential":[98],"frame-level":[99],"capable":[102],"learning":[104],"temporal":[105],"dynamics.":[106],"We":[107],"take":[111],"into":[112],"account":[113],"bottleneck":[114],"estimation.":[118],"experimental":[120],"results":[121],"show":[122,134],"that":[123],"proposed":[125,145],"method":[126],"can":[127],"obtain":[128],"accurate":[129],"they":[133],"good":[135],"generalization":[136],"ability":[137],"new":[139],"speakers":[140],"conditions.":[143],"significantly":[148],"outperforms":[149],"other":[150],"state-of-the-art":[151],"algorithms.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}