{"id":"https://openalex.org/W2143341575","doi":"https://doi.org/10.1109/tasl.2010.2064309","title":"A Probabilistic Interaction Model for Multipitch Tracking With Factorial Hidden Markov Models","display_name":"A Probabilistic Interaction Model for Multipitch Tracking With Factorial Hidden Markov Models","publication_year":2010,"publication_date":"2010-08-10","ids":{"openalex":"https://openalex.org/W2143341575","doi":"https://doi.org/10.1109/tasl.2010.2064309","mag":"2143341575"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2064309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2064309","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":"M Wohlmayr","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory (SPSC), Graz University of Technology, 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, 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":"middle","author":{"id":"https://openalex.org/A5006270785","display_name":"Michael Stark","orcid":"https://orcid.org/0000-0002-1481-9506"},"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":"M Stark","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory (SPSC), Graz University of Technology, 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, 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":"F Pernkopf","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory (SPSC), Graz University of Technology, 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, 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":3,"corresponding_author_ids":["https://openalex.org/A5079103786"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":5.7317,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.96667315,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"19","issue":"4","first_page":"799","last_page":"810"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9984999895095825,"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/timit","display_name":"TIMIT","score":0.6596719622612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6355310678482056},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.583048939704895},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5733546018600464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5697184801101685},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5579116344451904},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4703685939311981},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.46985307335853577},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43929511308670044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4105921983718872},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38312795758247375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32033175230026245}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6596719622612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6355310678482056},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.583048939704895},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5733546018600464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5697184801101685},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5579116344451904},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4703685939311981},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.46985307335853577},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43929511308670044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4105921983718872},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38312795758247375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32033175230026245}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2064309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2064309","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W41038521","https://openalex.org/W44831635","https://openalex.org/W50577135","https://openalex.org/W109581973","https://openalex.org/W129413713","https://openalex.org/W160800111","https://openalex.org/W1496562625","https://openalex.org/W1500640442","https://openalex.org/W1513861746","https://openalex.org/W1528056001","https://openalex.org/W1530235965","https://openalex.org/W1600397135","https://openalex.org/W1639266067","https://openalex.org/W1667165204","https://openalex.org/W1746680969","https://openalex.org/W1751091532","https://openalex.org/W1856744516","https://openalex.org/W1881757884","https://openalex.org/W1945090009","https://openalex.org/W1972240218","https://openalex.org/W1992402718","https://openalex.org/W2015143272","https://openalex.org/W2026129786","https://openalex.org/W2036488048","https://openalex.org/W2043694038","https://openalex.org/W2049073556","https://openalex.org/W2049633694","https://openalex.org/W2059833849","https://openalex.org/W2086725969","https://openalex.org/W2088632109","https://openalex.org/W2091425152","https://openalex.org/W2091696547","https://openalex.org/W2103135337","https://openalex.org/W2109886546","https://openalex.org/W2116324305","https://openalex.org/W2118740006","https://openalex.org/W2119599673","https://openalex.org/W2124149378","https://openalex.org/W2124369546","https://openalex.org/W2130322773","https://openalex.org/W2137813581","https://openalex.org/W2138084857","https://openalex.org/W2145678789","https://openalex.org/W2149095746","https://openalex.org/W2159202424","https://openalex.org/W2164266899","https://openalex.org/W2168098717","https://openalex.org/W2170491071","https://openalex.org/W2977466517","https://openalex.org/W6601652010","https://openalex.org/W6640608080","https://openalex.org/W6681658821","https://openalex.org/W6683207941"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2098101267","https://openalex.org/W2898606530","https://openalex.org/W2059119686","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"abstract_inverted_index":{"We":[0,18,133,151],"present":[1],"a":[2,42,65,123,163],"simple":[3],"and":[4,113,223],"efficient":[5],"feature":[6],"modeling":[7],"approach":[8],"for":[9,45,76,87,130,189,207],"tracking":[10,77,167,202],"the":[11,20,33,46,56,92,109,144,153,157,176,180,200,208,214,225],"pitch":[12,78,216],"of":[13,23,51,126,156,182,228],"two":[14],"simultaneously":[15],"active":[16],"speakers.":[17],"model":[19,37,59,73,83],"spectrogram":[21,49],"features":[22,50],"single":[24],"speakers":[25],"using":[26,137],"Gaussian":[27],"mixture":[28,48,57],"models":[29],"in":[30,160],"combination":[31],"with":[32],"minimum":[34],"description":[35],"length":[36],"selection":[38],"criterion.":[39],"To":[40],"obtain":[41],"probabilistic":[43],"representation":[44],"speech":[47,145,191,233],"both":[52],"speakers,":[53],"we":[54,107,121,195,212],"employ":[55],"maximization":[58],"(MIXMAX)":[60],"and,":[61],"as":[62,100,139,141],"an":[63],"alternative,":[64],"linear":[66,103],"interaction":[67,93],"model.":[68,104],"A":[69],"factorial":[70],"hidden":[71],"Markov":[72],"is":[74,187],"applied":[75],"over":[79],"time.":[80],"This":[81],"statistical":[82],"can":[84,97],"be":[85,98],"used":[86],"applications":[88],"beyond":[89],"speech,":[90],"whenever":[91],"between":[94],"individual":[95],"sources":[96],"represented":[99],"MIXMAX":[101],"or":[102],"For":[105],"tracking,":[106],"use":[108,213],"loopy":[110,127],"max-sum":[111],"algorithm,":[112],"provide":[114],"empirical":[115],"comparisons":[116],"to":[117,162,198,218],"exact":[118],"methods.":[119],"Furthermore,":[120],"discuss":[122],"scheduling":[124],"mechanism":[125],"belief":[128],"propagation":[129],"online":[131],"tracking.":[132],"demonstrate":[134,224],"experimental":[135],"results":[136],"Mocha-TIMIT":[138],"well":[140,164],"data":[142],"from":[143],"separation":[146,234],"challenge":[147],"provided":[148],"by":[149,204],"Cooke":[150],"show":[152],"excellent":[154],"performance":[155],"proposed":[158,177],"method":[159,178],"comparison":[161],"known":[165],"multipitch":[166],"algorithm":[168],"based":[169],"on":[170,232],"correlogram":[171],"features.":[172],"Using":[173],"speaker-dependent":[174,209],"models,":[175],"improves":[179],"accuracy":[181],"correct":[183,229],"speaker":[184,230],"assignment,":[185],"which":[186],"important":[188],"single-channel":[190,220],"separation.":[192],"In":[193],"particular,":[194],"are":[196],"able":[197],"reduce":[199],"overall":[201],"error":[203],"51%":[205],"relative":[206],"case.":[210],"Moreover,":[211],"estimated":[215],"trajectories":[217],"perform":[219],"source":[221],"separation,":[222],"beneficial":[226],"effect":[227],"assignment":[231],"performance.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}