{"id":"https://openalex.org/W2115129089","doi":"https://doi.org/10.1109/tasl.2010.2077280","title":"HMM-Based Multipitch Tracking for Noisy and Reverberant Speech","display_name":"HMM-Based Multipitch Tracking for Noisy and Reverberant Speech","publication_year":2010,"publication_date":"2010-09-20","ids":{"openalex":"https://openalex.org/W2115129089","doi":"https://doi.org/10.1109/tasl.2010.2077280","mag":"2115129089"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2077280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2077280","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5025797022","display_name":"Zhaozhang Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaozhang Jin","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":7.2964,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.97457241,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"19","issue":"5","first_page":"1091","last_page":"1102"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/reverberation","display_name":"Reverberation","score":0.7821102142333984},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7315712571144104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7312237620353699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685971200466156},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5372440814971924},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4666682779788971},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46631962060928345},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4646576941013336},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4518364369869232},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43178892135620117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3719409704208374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3664529025554657},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.29218924045562744}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7821102142333984},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7315712571144104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7312237620353699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685971200466156},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5372440814971924},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4666682779788971},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46631962060928345},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4646576941013336},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4518364369869232},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43178892135620117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3719409704208374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3664529025554657},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.29218924045562744},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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":2,"locations":[{"id":"doi:10.1109/tasl.2010.2077280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2077280","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.302.9838","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.302.9838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/%7Edwang/papers/Jin-Wang.taslp11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W86348706","https://openalex.org/W88864901","https://openalex.org/W160800111","https://openalex.org/W1728219059","https://openalex.org/W1881757884","https://openalex.org/W1974387177","https://openalex.org/W1984357105","https://openalex.org/W1998796903","https://openalex.org/W2004867530","https://openalex.org/W2027804983","https://openalex.org/W2043694038","https://openalex.org/W2048967079","https://openalex.org/W2091425152","https://openalex.org/W2107046066","https://openalex.org/W2117678320","https://openalex.org/W2118740006","https://openalex.org/W2119599673","https://openalex.org/W2122982914","https://openalex.org/W2125062731","https://openalex.org/W2148899569","https://openalex.org/W2149095746","https://openalex.org/W2149425615","https://openalex.org/W2159202424","https://openalex.org/W2163861656","https://openalex.org/W2166823384","https://openalex.org/W2172080951","https://openalex.org/W2561557072","https://openalex.org/W3127686677","https://openalex.org/W3193501227"],"related_works":["https://openalex.org/W2770624987","https://openalex.org/W4256175191","https://openalex.org/W2069517613","https://openalex.org/W4386336391","https://openalex.org/W2890085347","https://openalex.org/W2383417046","https://openalex.org/W3198667862","https://openalex.org/W3171794711","https://openalex.org/W3217417050","https://openalex.org/W2248536413"],"abstract_inverted_index":{"Multipitch":[0],"tracking":[1,33],"in":[2,13,34,105,120],"real":[3],"environments":[4],"is":[5,18],"critical":[6],"for":[7,31,63,89],"speech":[8,17],"signal":[9],"processing.":[10],"Determining":[11],"pitch":[12,61,65,77,85,92,103],"reverberant":[14,108,121],"and":[15,41,47,87,101,107],"noisy":[16,106],"a":[19,28,48],"particularly":[20,119],"challenging":[21],"task.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"propose":[27],"robust":[29],"algorithm":[30,96],"multipitch":[32],"the":[35,69,72,90],"presence":[36],"of":[37,71],"both":[38],"background":[39],"noise":[40],"room":[42],"reverberation.":[43],"An":[44],"auditory":[45],"front-end":[46],"new":[49],"channel":[50],"selection":[51],"method":[52],"are":[53],"utilized":[54],"to":[55],"extract":[56],"periodicity":[57,74],"features.":[58],"We":[59],"derive":[60],"scores":[62,86],"each":[64],"state,":[66],"which":[67],"estimate":[68],"likelihoods":[70],"observed":[73],"features":[75],"given":[76],"candidates.":[78],"A":[79],"hidden":[80],"Markov":[81],"model":[82],"integrates":[83],"these":[84],"searches":[88],"best":[91],"state":[93],"sequence.":[94],"Our":[95],"can":[97],"reliably":[98],"detect":[99],"single":[100],"double":[102],"contours":[104],"conditions.":[109,122],"Quantitative":[110],"evaluations":[111],"show":[112],"that":[113],"our":[114],"approach":[115],"outperforms":[116],"existing":[117],"ones,":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":12}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}