{"id":"https://openalex.org/W2102308274","doi":"https://doi.org/10.1109/icassp.2011.5947583","title":"Gain-robust multi-pitch tracking using sparse nonnegative matrix factorization","display_name":"Gain-robust multi-pitch tracking using sparse nonnegative matrix factorization","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2102308274","doi":"https://doi.org/10.1109/icassp.2011.5947583","mag":"2102308274"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5057485787","display_name":"Robert Peharz","orcid":"https://orcid.org/0000-0002-8644-9655"},"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":"Robert Peharz","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/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":false,"raw_author_name":"Michael 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":"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, 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/A5057485787"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67904768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5416","last_page":"5419"},"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/T11309","display_name":"Music 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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8106335401535034},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7550162076950073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5991171002388},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5384779572486877},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4679039418697357},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4522760510444641},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43959182500839233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43497687578201294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43466633558273315},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4292188584804535},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41163092851638794},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3584752082824707},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.08460801839828491}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8106335401535034},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7550162076950073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5991171002388},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5384779572486877},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4679039418697357},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4522760510444641},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43959182500839233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43497687578201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43466633558273315},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4292188584804535},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41163092851638794},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3584752082824707},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.08460801839828491},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:891613","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/891613/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1496562625","https://openalex.org/W1667165204","https://openalex.org/W1902027874","https://openalex.org/W1992402718","https://openalex.org/W2015143272","https://openalex.org/W2036488048","https://openalex.org/W2043252714","https://openalex.org/W2046245205","https://openalex.org/W2049633694","https://openalex.org/W2091425152","https://openalex.org/W2119599673","https://openalex.org/W2135029798","https://openalex.org/W2143341575","https://openalex.org/W2145678789","https://openalex.org/W2561557072","https://openalex.org/W2977466517","https://openalex.org/W3143596294","https://openalex.org/W6648237178","https://openalex.org/W6680012447","https://openalex.org/W6681658821","https://openalex.org/W7024001005","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291"],"abstract_inverted_index":{"While":[0],"nonnegative":[1],"matrix":[2],"factorization":[3],"(NMF)":[4],"has":[5],"successfully":[6],"been":[7],"applied":[8],"for":[9,80],"gain-robust":[10],"multi-pitch":[11],"detection,":[12],"a":[13,30,37,57,76,88],"method":[14],"to":[15,56],"track":[16],"pitch":[17,27],"values":[18],"over":[19],"time":[20],"was":[21],"not":[22],"provided.":[23],"We":[24,65],"embed":[25],"NMF-based":[26],"detection":[28],"into":[29],"recently":[31],"proposed":[32],"pitch-tracking":[33],"system,":[34],"based":[35],"on":[36],"factorial":[38],"hidden":[39],"Markov":[40],"model":[41,79],"(FHMM).":[42],"The":[43],"original":[44,120],"system":[45],"models":[46],"speech":[47],"spectra":[48],"with":[49,102],"Gaussian":[50],"mixture":[51],"models,":[52],"which":[53,97],"is":[54],"sensitive":[55],"gain":[58],"mismatch":[59],"between":[60],"training":[61,84],"and":[62,74],"test":[63],"data.":[64],"therefore":[66],"combine":[67],"the":[68,81,99,111,116,119],"advantages":[69],"of":[70,90,118],"these":[71],"two":[72],"approaches":[73],"derive":[75],"gain-adaptive":[77],"observation":[78],"FHMM.":[82],"As":[83],"algorithm":[85],"we":[86,108],"use":[87],"modification":[89],"\u2113":[91],"<sup":[92],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[93],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sup>":[94],"-sparse":[95],"NMF,":[96],"represents":[98],"short-time":[100],"spectrum":[101],"scalable":[103],"basis":[104],"vectors.":[105],"In":[106],"experiments":[107],"show":[109],"that":[110],"new":[112],"approach":[113],"significantly":[114],"increases":[115],"gain-robustness":[117],"tracking":[121],"system.":[122]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}