{"id":"https://openalex.org/W2022798421","doi":"https://doi.org/10.1109/tasl.2013.2260744","title":"Model-Based Multiple Pitch Tracking Using Factorial HMMs: Model Adaptation and Inference","display_name":"Model-Based Multiple Pitch Tracking Using Factorial HMMs: Model Adaptation and Inference","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2022798421","doi":"https://doi.org/10.1109/tasl.2013.2260744","mag":"2022798421"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2260744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2260744","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/A5079103786","display_name":"Michael Wohlmayr","orcid":null},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Michael Wohlmayr","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory (SPSC), Graz University of Technology, Graz, Austria","Signal Process. & Speech Commun. Lab. (SPSC), Graz Univ. of Technol., Graz, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory (SPSC), Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Process. & Speech Commun. Lab. (SPSC), Graz Univ. of Technol., Graz, Austria#TAB#","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015798259","display_name":"Franz Pernkopf","orcid":"https://orcid.org/0000-0002-6356-3367"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory (SPSC), Graz University of Technology, Graz, Austria","Signal Process. & Speech Commun. Lab. (SPSC), Graz Univ. of Technol., Graz, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory (SPSC), Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Process. & Speech Commun. Lab. (SPSC), Graz Univ. of Technol., Graz, Austria#TAB#","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079103786"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":1.9286,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85954797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"8","first_page":"1742","last_page":"1754"},"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":0.9998000264167786,"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":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.7653908133506775},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.727998673915863},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7155588865280151},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6621599197387695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5373761653900146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5056171417236328},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5048745274543762},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48603469133377075},{"id":"https://openalex.org/keywords/factorial","display_name":"Factorial","score":0.4116877615451813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10630398988723755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653908133506775},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.727998673915863},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7155588865280151},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6621599197387695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5373761653900146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056171417236328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5048745274543762},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48603469133377075},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.4116877615451813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10630398988723755},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2013.2260744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2260744","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:10.1.1.337.8158","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.337.8158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W80444264","https://openalex.org/W86348706","https://openalex.org/W1528056001","https://openalex.org/W1574263887","https://openalex.org/W1602659231","https://openalex.org/W1800365115","https://openalex.org/W1902027874","https://openalex.org/W1989954041","https://openalex.org/W1991139021","https://openalex.org/W2005608041","https://openalex.org/W2008565517","https://openalex.org/W2015143272","https://openalex.org/W2029564985","https://openalex.org/W2037740282","https://openalex.org/W2049633694","https://openalex.org/W2060822897","https://openalex.org/W2079362249","https://openalex.org/W2100969003","https://openalex.org/W2103137138","https://openalex.org/W2119599673","https://openalex.org/W2124149378","https://openalex.org/W2130322773","https://openalex.org/W2131816934","https://openalex.org/W2138084857","https://openalex.org/W2143341575","https://openalex.org/W2144271355","https://openalex.org/W2146871184","https://openalex.org/W2149425615","https://openalex.org/W2150415460","https://openalex.org/W2150833111","https://openalex.org/W2155531311","https://openalex.org/W2165108269","https://openalex.org/W2403891086","https://openalex.org/W2404067064","https://openalex.org/W2567948266","https://openalex.org/W2610184409","https://openalex.org/W2977466517","https://openalex.org/W4210849719","https://openalex.org/W4212863985","https://openalex.org/W4245919820","https://openalex.org/W4250589301","https://openalex.org/W4299729612","https://openalex.org/W6603255414","https://openalex.org/W6675616813","https://openalex.org/W6713287732","https://openalex.org/W6713478990","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W2164162849"],"abstract_inverted_index":{"Robustness":[0],"against":[1],"noise":[2],"and":[3,15,73,139],"interfering":[4],"audio":[5,16],"signals":[6],"is":[7,25,87,113,122],"one":[8],"of":[9,36,148],"the":[10,61,91,95,117,146,152],"challenges":[11],"in":[12,63,120],"speech":[13,107],"recognition":[14],"analysis":[17],"technology.":[18],"One":[19],"avenue":[20],"to":[21,89,94,115],"approach":[22],"this":[23,67],"challenge":[24],"single-channel":[26],"multiple-source":[27],"modeling.":[28],"Factorial":[29],"hidden":[30],"Markov":[31],"models":[32,48,72],"(FHMMs)":[33],"are":[34,56,142],"capable":[35,88],"modeling":[37],"acoustic":[38,102],"scenes":[39],"with":[40],"multiple":[41],"sources":[42],"interacting":[43],"over":[44],"time.":[45],"While":[46],"these":[47,71],"reach":[49],"good":[50],"performance":[51],"on":[52,133],"specific":[53,96],"tasks,":[54],"there":[55],"still":[57],"serious":[58],"limitations":[59],"restricting":[60],"applicability":[62],"many":[64],"domains.":[65],"In":[66,77],"paper,":[68],"we":[69,79],"generalize":[70],"enhance":[74],"their":[75],"applicability.":[76],"particular,":[78],"develop":[80,129],"an":[81,123],"EM-like":[82],"iterative":[83],"adaptation":[84,138],"framework":[85],"which":[86],"adapt":[90],"model":[92],"parameters":[93],"situation":[97],"(e.g.":[98],"actual":[99],"speakers,":[100],"gain,":[101],"channel,":[103],"etc.)":[104],"using":[105,151],"only":[106],"mixture":[108],"data.":[109],"Currently,":[110],"source-specific":[111],"data":[112],"required":[114],"learn":[116],"model.":[118],"Inference":[119],"FHMMs":[121],"essential":[124],"ingredient":[125],"for":[126,145],"adaptation.":[127],"We":[128],"efficient":[130,140],"approaches":[131],"based":[132],"observation":[134],"likelihood":[135],"pruning.":[136],"Both":[137],"inference":[141],"empirically":[143],"evaluated":[144],"task":[147],"multipitch":[149],"tracking":[150],"GRID":[153],"corpus.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}