{"id":"https://openalex.org/W2155444361","doi":"https://doi.org/10.1109/icassp.2009.4959529","title":"Towards source-filter based single sensor speech separation","display_name":"Towards source-filter based single sensor speech separation","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2155444361","doi":"https://doi.org/10.1109/icassp.2009.4959529","mag":"2155444361"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/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":true,"raw_author_name":"Michael Stark","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","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"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006270785"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":0.3525,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60600731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"97","last_page":"100"},"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":0.9993000030517578,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7452501058578491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6614924669265747},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6206575632095337},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6196126937866211},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5720416307449341},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5304854512214661},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5155979990959167},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4642553925514221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4372541308403015},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4367717206478119},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.43557700514793396},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43257856369018555},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40042030811309814},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08281511068344116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07286828756332397}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7452501058578491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614924669265747},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6206575632095337},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6196126937866211},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5720416307449341},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5304854512214661},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5155979990959167},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4642553925514221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4372541308403015},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4367717206478119},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.43557700514793396},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43257856369018555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40042030811309814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08281511068344116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07286828756332397},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4959529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W1508165687","https://openalex.org/W2015143272","https://openalex.org/W2030534537","https://openalex.org/W2097191389","https://openalex.org/W2149425615","https://openalex.org/W2168793898","https://openalex.org/W2969767819","https://openalex.org/W4214498238","https://openalex.org/W6684458083","https://openalex.org/W6766977873"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2470236000","https://openalex.org/W2097143083","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743","https://openalex.org/W2386453889"],"abstract_inverted_index":{"We":[0,64],"present":[1],"a":[2,18,37,61],"new":[3],"source-filter":[4],"based":[5],"method":[6,98],"to":[7,94],"separate":[8],"two":[9],"speakers":[10,31],"talking":[11],"simultaneously":[12],"at":[13],"equal":[14],"level":[15],"mixed":[16],"into":[17],"single":[19,124],"sensor.":[20],"First,":[21],"the":[22,25,30,47,68,95,105,119],"relation":[23],"between":[24],"spectral":[26],"whitened":[27],"mixture":[28,97],"and":[29,115],"excitation":[32,49],"signals":[33,50],"is":[34,44,87,107],"analyzed.":[35],"Therefore,":[36],"factorial":[38],"HMM":[39],"capturing":[40],"also":[41],"time":[42],"dependencies":[43],"exploited.":[45],"Then,":[46],"estimated":[48],"are":[51],"combined":[52],"with":[53],"best":[54],"fitting":[55],"vocal":[56],"tract":[57],"information":[58],"taken":[59],"from":[60],"trained":[62],"dictionary.":[63],"report":[65],"results":[66],"on":[67,101],"database":[69],"of":[70,79,121],"Cooke":[71],"considering":[72],"108":[73],"speech":[74,126],"mixtures.":[75],"The":[76],"average":[77],"improvement":[78],"2.9":[80],"dB":[81],"in":[82,112],"SIR":[83],"for":[84],"all":[85],"data":[86],"lower":[88,92],"but":[89],"not":[90],"significantly":[91],"compared":[93],"Gaussian":[96],"which":[99],"relies":[100],"known":[102],"pitch-tracks.":[103],"Although":[104],"performance":[106],"currently":[108],"moderate":[109],"we":[110],"believe":[111],"this":[113],"approach":[114],"its":[116],"significance":[117],"towards":[118],"development":[120],"speaker":[122],"independent":[123],"sensor":[125],"separation.":[127]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}