{"id":"https://openalex.org/W2141820426","doi":"https://doi.org/10.1109/icassp.2010.5495048","title":"A mixture maximization approach to multipitch tracking with factorial hidden Markov models","display_name":"A mixture maximization approach to multipitch tracking with factorial hidden Markov models","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2141820426","doi":"https://doi.org/10.1109/icassp.2010.5495048","mag":"2141820426"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/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, Graz University of Technology, Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, 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, Graz University of Technology, Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, 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, Graz University of Technology, Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, 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":0.3371,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60647127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"5070","last_page":"5073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.994700014591217,"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":0.994700014591217,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9871000051498413,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9742000102996826,"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/correlogram","display_name":"Correlogram","score":0.7288044691085815},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7113531827926636},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6676150560379028},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.593712329864502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5515720844268799},{"id":"https://openalex.org/keywords/factorial","display_name":"Factorial","score":0.5340313911437988},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5302956700325012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5236746668815613},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5063399076461792},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.41755327582359314},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4166494607925415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35597580671310425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32656753063201904},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.3068561553955078},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21416914463043213},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.14017248153686523}],"concepts":[{"id":"https://openalex.org/C196070930","wikidata":"https://www.wikidata.org/wiki/Q598190","display_name":"Correlogram","level":2,"score":0.7288044691085815},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7113531827926636},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6676150560379028},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.593712329864502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5515720844268799},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.5340313911437988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5302956700325012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5236746668815613},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5063399076461792},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.41755327582359314},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4166494607925415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35597580671310425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32656753063201904},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.3068561553955078},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21416914463043213},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.14017248153686523},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W41038521","https://openalex.org/W145027662","https://openalex.org/W1528056001","https://openalex.org/W1530235965","https://openalex.org/W1746680969","https://openalex.org/W1881757884","https://openalex.org/W1945090009","https://openalex.org/W2015143272","https://openalex.org/W2043694038","https://openalex.org/W2119599673","https://openalex.org/W2124369546","https://openalex.org/W2130322773","https://openalex.org/W2137813581","https://openalex.org/W2170491071","https://openalex.org/W3129711340","https://openalex.org/W6631886430","https://openalex.org/W6640608080","https://openalex.org/W6790626572"],"related_works":["https://openalex.org/W2760460304","https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W314641344","https://openalex.org/W2088854863","https://openalex.org/W3175941393","https://openalex.org/W2115956902","https://openalex.org/W1853799209","https://openalex.org/W2124369546"],"abstract_inverted_index":{"We":[0,18,70],"present":[1],"a":[2,51,61,89],"simple":[3],"and":[4,77],"efficient":[5],"feature":[6],"modeling":[7],"approach":[8],"for":[9,54,68],"tracking":[10,93],"the":[11,20,33,41,55,79,83],"pitch":[12],"of":[13,23,57,82],"two":[14,75],"speakers":[15,25],"speaking":[16],"simultaneously.":[17],"model":[19,37,46,65],"spectrogram":[21],"features":[22],"single":[24],"using":[26],"Gaussian":[27],"mixture":[28,42,56],"models":[29],"in":[30,86],"combination":[31],"with":[32],"minimum":[34],"description":[35],"length":[36],"selection":[38],"criterion.":[39],"Furthermore,":[40],"maximization":[43],"(MIXMAX)":[44],"interaction":[45],"is":[47,66],"employed":[48],"to":[49,88],"yield":[50],"probabilistic":[52],"representation":[53],"both":[58],"speakers.":[59],"Finally,":[60],"factorial":[62],"hidden":[63],"Markov":[64],"applied":[67],"tracking.":[69],"demonstrate":[71],"experimental":[72],"results":[73],"on":[74,96],"databases,":[76],"show":[78],"excellent":[80],"performance":[81],"proposed":[84],"method":[85],"comparison":[87],"well":[90],"known":[91],"multipitch":[92],"algorithm":[94],"based":[95],"correlogram":[97],"features.":[98]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}