{"id":"https://openalex.org/W2029564985","doi":"https://doi.org/10.1109/icassp.2010.5495323","title":"Scaled factorial hidden Markov models: A new technique for compensating gain differences in model-based single channel speech separation","display_name":"Scaled factorial hidden Markov models: A new technique for compensating gain differences in model-based single channel speech separation","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2029564985","doi":"https://doi.org/10.1109/icassp.2010.5495323","mag":"2029564985"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495323","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/A5084531219","display_name":"Mohammad Hadi Radfar","orcid":"https://orcid.org/0000-0001-8535-1384"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Martin Radfar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Canada","Dept. of Electrical and Computer Eng., Univ. of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Eng., Univ. of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024382401","display_name":"Willy Wong","orcid":"https://orcid.org/0000-0002-3900-3140"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"W. Wong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Canada","Dept. of Electrical and Computer Eng., Univ. of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Eng., Univ. of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001546768","display_name":"Richard M. Dansereau","orcid":"https://orcid.org/0000-0002-3512-3647"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"R. M. Dansereau","raw_affiliation_strings":["Department of Systems and Computer Engineering, Carleton University, Ottawa, Canada","[Department of Systems and Computer Engineering, Carleton University, Ottawa, Canada.]"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Computer Engineering, Carleton University, Ottawa, Canada","institution_ids":["https://openalex.org/I67031392"]},{"raw_affiliation_string":"[Department of Systems and Computer Engineering, Carleton University, Ottawa, Canada.]","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110245214","display_name":"W.-Y. Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"W.-Y. Chan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Queen's University, Kingston, Canada","Dept. of Electrical and Computer Engineering, Queen\u2019s University Kingston, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Queen's University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Queen\u2019s University Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084531219"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":3.0344,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9165532,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1918","last_page":"1921"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991000294685364,"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/factorial","display_name":"Factorial","score":0.6464939713478088},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6076784133911133},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5653784275054932},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5294995307922363},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5254099369049072},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5023398399353027},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4901154935359955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47360944747924805},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46159788966178894},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4558289647102356},{"id":"https://openalex.org/keywords/factorial-experiment","display_name":"Factorial experiment","score":0.45328620076179504},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4531148672103882},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4189378619194031},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.413828045129776},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4110289216041565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3872528076171875},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24695292115211487}],"concepts":[{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.6464939713478088},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6076784133911133},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5653784275054932},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5294995307922363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5254099369049072},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5023398399353027},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4901154935359955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47360944747924805},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46159788966178894},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4558289647102356},{"id":"https://openalex.org/C169222746","wikidata":"https://www.wikidata.org/wiki/Q4116558","display_name":"Factorial experiment","level":2,"score":0.45328620076179504},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4531148672103882},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4189378619194031},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.413828045129776},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4110289216041565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3872528076171875},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24695292115211487},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495323","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W76572587","https://openalex.org/W80444264","https://openalex.org/W1528056001","https://openalex.org/W2015143272","https://openalex.org/W2057220308","https://openalex.org/W2111070087","https://openalex.org/W2146608839","https://openalex.org/W2149648698","https://openalex.org/W2168793898","https://openalex.org/W4245655784","https://openalex.org/W6684458083"],"related_works":["https://openalex.org/W2167131998","https://openalex.org/W4365453583","https://openalex.org/W4229629925","https://openalex.org/W1633163079","https://openalex.org/W2792127186","https://openalex.org/W2002931749","https://openalex.org/W4283718311","https://openalex.org/W4210897036","https://openalex.org/W3203873370","https://openalex.org/W4229861962"],"abstract_inverted_index":{"In":[0,67,83],"model-based":[1],"single":[2],"channel":[3],"speech":[4,32,151],"separation,":[5],"factorial":[6],"hidden":[7],"Markov":[8],"models":[9],"(FHMM)":[10],"have":[11],"been":[12],"successfully":[13],"applied":[14],"to":[15,74,109,135],"model":[16],"the":[17,31,39,46,61,87,95,114,119,122,140],"mixture":[18,123],"signal":[19],"Y(t)":[20],"=":[21],"X(t)":[22,34,54],"+":[23],"V(t)":[24],"in":[25,92],"terms":[26,93],"of":[27,30,45,63,94,121],"trained":[28,47],"patterns":[29,48],"signals":[33,41],"and":[35,55,147],"V(t).":[36],"Nonetheless,":[37],"when":[38],"test":[40],"are":[42,90],"scaled":[43,77],"versions":[44],"(i.e.":[49],"g":[50,56],"<sub":[51,57],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[52,58],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">x</sub>":[53],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">v</sub>":[59],"V(t)),":[60],"performance":[62],"FHMM":[64,108],"degrades":[65],"significantly.":[66],"this":[68,84],"paper,":[69],"we":[70],"introduce":[71],"a":[72],"modification":[73],"FHMM,":[75,78,146],"called":[76],"which":[79,112],"compensates":[80],"gain":[81],"difference.":[82],"technique,":[85],"first,":[86],"scale":[88],"factors":[89],"expressed":[91],"target-to-interference":[96],"ratio":[97],"(TIR).":[98],"Then,":[99],"an":[100],"iteration":[101],"quadratic":[102],"optimization":[103],"approach":[104],"is":[105],"coupled":[106],"with":[107,113,131],"estimate":[110],"TIR":[111],"decoded":[115],"HMM":[116],"sequences":[117],"maximize":[118],"likelihood":[120],"signal.":[124],"Experimental":[125],"results,":[126],"conducted":[127],"on":[128],"180":[129],"mixtures":[130],"TIRs":[132],"from":[133],"0":[134],"15":[136],"dB,":[137],"show":[138],"that":[139],"proposed":[141],"technique":[142],"significantly":[143],"outperforms":[144],"unscaled":[145],"scaled/unscaled":[148],"vector":[149],"quantization":[150],"separation":[152],"techniques.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}