{"id":"https://openalex.org/W2407051648","doi":"https://doi.org/10.1109/icassp.2016.7472931","title":"F0 estimation for noisy speech by exploring temporal harmonic structures in local time frequency spectrum segment","display_name":"F0 estimation for noisy speech by exploring temporal harmonic structures in local time frequency spectrum segment","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407051648","doi":"https://doi.org/10.1109/icassp.2016.7472931","mag":"2407051648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5100408281","display_name":"Dongmei Wang","orcid":"https://orcid.org/0000-0002-6930-0066"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongmei Wang","raw_affiliation_strings":["Dept. Electrical Engineering, University of Texas at Dallas, Richardson, Tx"],"affiliations":[{"raw_affiliation_string":"Dept. Electrical Engineering, University of Texas at Dallas, Richardson, Tx","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Dept. Electrical Engineering, University of Texas at Dallas, Richardson, Tx"],"affiliations":[{"raw_affiliation_string":"Dept. Electrical Engineering, University of Texas at Dallas, Richardson, Tx","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100408281"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":1.2609,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80231035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"6510","last_page":"6514"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.6934518814086914},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6657650470733643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6309915781021118},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6057926416397095},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6022738218307495},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5812041759490967},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5507912039756775},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5382570624351501},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.47179263830184937},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.4372524917125702},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.41348710656166077},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.41157710552215576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32440218329429626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2665095925331116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2026674747467041},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16009575128555298},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15565654635429382},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.15553045272827148},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09899044036865234},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08448591828346252}],"concepts":[{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.6934518814086914},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6657650470733643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309915781021118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6057926416397095},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6022738218307495},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5812041759490967},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5507912039756775},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5382570624351501},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.47179263830184937},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.4372524917125702},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.41348710656166077},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.41157710552215576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32440218329429626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2665095925331116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2026674747467041},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16009575128555298},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15565654635429382},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.15553045272827148},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09899044036865234},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08448591828346252},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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":34,"referenced_works":["https://openalex.org/W23669922","https://openalex.org/W86348706","https://openalex.org/W1592520011","https://openalex.org/W1886421314","https://openalex.org/W1968652492","https://openalex.org/W1990449877","https://openalex.org/W1993064527","https://openalex.org/W2018637815","https://openalex.org/W2028078738","https://openalex.org/W2033035341","https://openalex.org/W2034300186","https://openalex.org/W2038279487","https://openalex.org/W2052252043","https://openalex.org/W2075076415","https://openalex.org/W2088846517","https://openalex.org/W2091425152","https://openalex.org/W2092387354","https://openalex.org/W2100384625","https://openalex.org/W2100656565","https://openalex.org/W2100989275","https://openalex.org/W2118740006","https://openalex.org/W2118774185","https://openalex.org/W2119599673","https://openalex.org/W2135431242","https://openalex.org/W2167003379","https://openalex.org/W2171840027","https://openalex.org/W2173716127","https://openalex.org/W2398521182","https://openalex.org/W2404934284","https://openalex.org/W4252750563","https://openalex.org/W6635339914","https://openalex.org/W6659204540","https://openalex.org/W6677411890","https://openalex.org/W6712654940"],"related_works":["https://openalex.org/W2394544468","https://openalex.org/W2056455302","https://openalex.org/W2587667458","https://openalex.org/W2068237456","https://openalex.org/W1861882962","https://openalex.org/W2109998678","https://openalex.org/W2164070943","https://openalex.org/W2163128389","https://openalex.org/W2121926536","https://openalex.org/W1497667432"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,53],"propose":[4],"a":[5,84],"noise":[6,63],"robust":[7],"F0":[8,57,80,90,105,122],"estimation":[9,82,123],"approach":[10,114],"by":[11],"exploring":[12],"the":[13,24,31,34,40,94,104,116],"temporal":[14,106],"harmonic":[15,36],"structures":[16,37],"in":[17,39,119],"local":[18],"time-frequency":[19],"(TF)":[20],"spectrum":[21],"segment.":[22],"Since":[23],"speech":[25,35,42],"energy":[26,43],"is":[27],"sparsely":[28],"distributed":[29],"on":[30,93],"TF":[32,44,66,87,99],"plane,":[33],"occupied":[38],"higher":[41],"segment":[45,100],"are":[46],"tending":[47],"to":[48,55,62],"dominate":[49],"over":[50],"noise.":[51],"Thus,":[52],"attempt":[54],"derive":[56],"from":[58],"such":[59],"high":[60],"(signal":[61],"ratio)":[64],"SNR":[65],"segments":[67],"rather":[68],"than":[69],"full":[70],"band":[71],"signal.":[72],"Our":[73],"algorithm":[74],"comprises":[75],"of":[76,86,97,121],"two":[77],"stages:":[78],"i)":[79],"candidate":[81],"for":[83],"series":[85],"segments;":[88],"ii)":[89],"tracking":[91],"based":[92],"acoustic":[95],"features":[96],"each":[98],"as":[101,103],"well":[102],"continuity":[107],"constraints.":[108],"Experimental":[109],"results":[110],"show":[111],"that":[112],"our":[113],"outperforms":[115],"compared":[117],"methods":[118],"terms":[120],"accuracy.":[124]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}