{"id":"https://openalex.org/W145027662","doi":"https://doi.org/10.21437/interspeech.2008-34","title":"Multipitch tracking using a factorial hidden Markov model","display_name":"Multipitch tracking using a factorial hidden Markov model","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W145027662","doi":"https://doi.org/10.21437/interspeech.2008-34","mag":"145027662"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-34","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-34","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Wohlmayr","raw_affiliation_strings":["Institute of Signal Processing and Speech Communication (4420)"],"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing and Speech Communication (4420)","institution_ids":["https://openalex.org/I4210121626"]}]},{"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/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Institute of Signal Processing and Speech Communication (4420)"],"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing and Speech Communication (4420)","institution_ids":["https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079103786"],"corresponding_institution_ids":["https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":0.7465,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68728385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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":0.9965000152587891,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8529417514801025},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7508096098899841},{"id":"https://openalex.org/keywords/correlogram","display_name":"Correlogram","score":0.7153834104537964},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6842322945594788},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6787203550338745},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5213987827301025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49524179100990295},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.41584882140159607},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4103074073791504}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8529417514801025},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7508096098899841},{"id":"https://openalex.org/C196070930","wikidata":"https://www.wikidata.org/wiki/Q598190","display_name":"Correlogram","level":2,"score":0.7153834104537964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6842322945594788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6787203550338745},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5213987827301025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49524179100990295},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.41584882140159607},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4103074073791504},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2008-34","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-34","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1528056001","https://openalex.org/W1530235965","https://openalex.org/W1746680969","https://openalex.org/W2043694038","https://openalex.org/W2119599673","https://openalex.org/W2137813581","https://openalex.org/W2140053068","https://openalex.org/W2170491071"],"related_works":["https://openalex.org/W2760460304","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W4319777828","https://openalex.org/W2340308015","https://openalex.org/W2283180889"],"abstract_inverted_index":{"In":[0,37],"this":[1],"paper,":[2],"we":[3,25,53],"present":[4],"an":[5],"approach":[6,68],"to":[7,39,84],"track":[8,26],"the":[9,23,27,40,70,82,85],"pitch":[10,58,105],"of":[11,74],"two":[12],"simultaneous":[13],"speakers.":[14,64],"Using":[15],"a":[16,31,51,92],"well-known":[17],"feature":[18],"extraction":[19],"method":[20],"based":[21,49],"on":[22,50,69],"correlogram,":[24],"resulting":[28],"data":[29],"using":[30],"factorial":[32],"hidden":[33],"Markov":[34],"model":[35],"(FHMM).":[36],"contrast":[38],"recently":[41],"developed":[42],"multipitch":[43,86],"determination":[44,87],"algorithm":[45,88],"[1],":[46],"which":[47],"is":[48],"HMM,":[52],"can":[54],"accurately":[55],"associate":[56],"estimated":[57],"points":[59],"with":[60],"their":[61],"corresponding":[62],"source":[63],"We":[65],"evalute":[66],"our":[67,97],"\u201cMocha-TIMIT\u201d":[71],"database":[72],"[2]":[73],"speech":[75],"utterances":[76],"mixed":[77],"at":[78],"0dB,":[79],"and":[80,107],"compare":[81],"results":[83],"[1]":[89],"used":[90],"as":[91],"baseline.":[93],"Experiments":[94],"show":[95],"that":[96],"FHMM":[98],"tracker":[99],"yields":[100],"good":[101],"performance":[102],"for":[103],"both":[104],"estimation":[106],"correct":[108],"speaker":[109],"assignment.":[110]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}