{"id":"https://openalex.org/W2085628288","doi":"https://doi.org/10.1109/icassp.2014.6854049","title":"A pitch extraction algorithm tuned for automatic speech recognition","display_name":"A pitch extraction algorithm tuned for automatic speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2085628288","doi":"https://doi.org/10.1109/icassp.2014.6854049","mag":"2085628288"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5029777844","display_name":"Pegah Ghahremani","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pegah Ghahremani","raw_affiliation_strings":["Johns Hopkins University","Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004810529","display_name":"Bagher BabaAli","orcid":"https://orcid.org/0000-0001-8064-580X"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Bagher BabaAli","raw_affiliation_strings":["University of Tehran, Iran","University of Tehran , Tehran , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"University of Tehran , Tehran , Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Johns Hopkins University","Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053498662","display_name":"Korbinian Riedhammer","orcid":"https://orcid.org/0000-0003-3582-2154"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Korbinian Riedhammer","raw_affiliation_strings":["ICSI, Berkeley","ICSI, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICSI, Berkeley","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"ICSI, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Trmal","raw_affiliation_strings":["Johns Hopkins University","Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University","Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":296,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2494","last_page":"2498"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/voice","display_name":"Voice","score":0.8397558927536011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7566511034965515},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.716683566570282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6691015958786011},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.6120773553848267},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5413491725921631},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4789472222328186},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.45075979828834534},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34582746028900146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33753061294555664},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1354716718196869},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11979460716247559},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08757442235946655}],"concepts":[{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.8397558927536011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566511034965515},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.716683566570282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6691015958786011},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.6120773553848267},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5413491725921631},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4789472222328186},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.45075979828834534},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34582746028900146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33753061294555664},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1354716718196869},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11979460716247559},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08757442235946655},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W23669922","https://openalex.org/W1524333225","https://openalex.org/W1571901760","https://openalex.org/W1975079546","https://openalex.org/W1981706894","https://openalex.org/W2089537772","https://openalex.org/W2091425152","https://openalex.org/W2115098197","https://openalex.org/W2119599673","https://openalex.org/W2125234026","https://openalex.org/W2129070077","https://openalex.org/W2135431242","https://openalex.org/W2442329935","https://openalex.org/W3141523618","https://openalex.org/W6631362777","https://openalex.org/W6679097437","https://openalex.org/W6718561954"],"related_works":["https://openalex.org/W1537109791","https://openalex.org/W2379831147","https://openalex.org/W2388176952","https://openalex.org/W2039878594","https://openalex.org/W2941168791","https://openalex.org/W2117854015","https://openalex.org/W2029025464","https://openalex.org/W2066867401","https://openalex.org/W2356656526","https://openalex.org/W2138039466"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,44,52,75,91],"present":[4,137],"an":[5],"algorithm":[6,108],"that":[7,113,131],"produces":[8,110],"pitch":[9,49,94,102,133,161],"and":[10,34,148,158,162],"probability-of-voicing":[11],"estimates":[12],"for":[13,31,38],"use":[14],"as":[15,117],"features":[16,23,157],"in":[17,144],"automatic":[18],"speech":[19],"recognition":[20],"systems.":[21],"These":[22],"give":[24],"large":[25,151],"performance":[26],"improvements":[27,37],"on":[28,126,139],"tonal":[29,156],"languages":[30,143],"ASR":[32,59],"systems,":[33],"even":[35,95],"substantial":[36],"non-tonal":[39],"languages.":[40],"Our":[41,107],"method,":[42],"which":[43],"are":[45,53],"calling":[46],"the":[47,57,67,72,101,127,145],"Kaldi":[48,58],"tracker":[50],"(because":[51],"adding":[54],"it":[55,123],"to":[56,96,104],"toolkit),":[60],"is":[61,86,124],"a":[62,79,93,111,118,150],"highly":[63],"modified":[64],"version":[65],"of":[66,120],"getf0":[68,74],"(RAPT)":[69],"algorithm.":[70],"Unlike":[71],"original":[73],"do":[76],"not":[77],"make":[78],"hard":[80],"decision":[81],"whether":[82],"any":[83],"given":[84],"frame":[85],"voiced":[87],"or":[88,169],"unvoiced;":[89],"instead,":[90],"assign":[92],"unvoiced":[97],"frames":[98],"while":[99],"constraining":[100],"trajectory":[103],"be":[105,115],"continuous.":[106],"also":[109],"quantity":[112],"can":[114],"used":[116],"probability":[119],"voicing":[121],"measure;":[122],"based":[125],"normalized":[128],"autocorrelation":[129],"measure":[130],"our":[132],"extractor":[134],"uses.":[135],"We":[136],"results":[138],"data":[140],"from":[141,167],"various":[142],"BABEL":[146],"project,":[147],"show":[149],"improvement":[152],"over":[153],"systems":[154,159],"without":[155],"where":[160],"POV":[163],"information":[164],"was":[165],"obtained":[166],"SAcC":[168],"getf0.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":32},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":34},{"year":2014,"cited_by_count":15}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}