{"id":"https://openalex.org/W2148411006","doi":"https://doi.org/10.1109/icassp.2012.6288806","title":"Indirect model-based speech enhancement","display_name":"Indirect model-based speech enhancement","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2148411006","doi":"https://doi.org/10.1109/icassp.2012.6288806","mag":"2148411006"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"4045","last_page":"4048"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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-enhancement","display_name":"Speech enhancement","score":0.7451660633087158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6394683122634888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6152641773223877},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.574512243270874},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.5418648719787598},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.46293726563453674},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4414319694042206},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4308116137981415},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42872896790504456},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42383551597595215},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3479984998703003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2545333802700043},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1759585738182068},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10636758804321289}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7451660633087158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6394683122634888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6152641773223877},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.574512243270874},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.5418648719787598},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.46293726563453674},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4414319694042206},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4308116137981415},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42872896790504456},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42383551597595215},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3479984998703003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2545333802700043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1759585738182068},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10636758804321289},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2012.6288806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.374.8770","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.374.8770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.merl.com/publications/docs/TR2012-016.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.715.1487","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.715.1487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jonathanleroux.org/pdf/LeRoux2012ICASSP03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W174003511","https://openalex.org/W1638866737","https://openalex.org/W1911988225","https://openalex.org/W2044721031","https://openalex.org/W2105696145","https://openalex.org/W2112089769","https://openalex.org/W2121973264","https://openalex.org/W2124611315","https://openalex.org/W2126597753","https://openalex.org/W2127851351","https://openalex.org/W2128402994","https://openalex.org/W2128653836","https://openalex.org/W2146324387","https://openalex.org/W2165967438","https://openalex.org/W2170256193","https://openalex.org/W2197686235","https://openalex.org/W2273833408","https://openalex.org/W2404684379","https://openalex.org/W3147539069","https://openalex.org/W6607061495","https://openalex.org/W6676877154"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W193702574","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W1523214805","https://openalex.org/W4294771049","https://openalex.org/W2559040841","https://openalex.org/W2341426843","https://openalex.org/W2121894251","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Model-based":[0],"speech":[1,18,26,30,89],"enhancement":[2],"methods,":[3],"such":[4],"as":[5],"vector-Taylor":[6],"series-based":[7],"methods":[8],"(VTS)":[9],"[1,":[10],"2],":[11],"share":[12],"a":[13,32],"common":[14],"methodology:":[15],"they":[16],"estimate":[17,64],"using":[19],"the":[20,24,28,44,48,51,57,66,79,86],"expected":[21,45],"value":[22,46],"of":[23,47,65,81,105],"clean":[25],"given":[27],"noisy":[29,58],"under":[31,50],"statistical":[33],"model.":[34],"We":[35],"show":[36],"that":[37],"it":[38,55],"may":[39],"be":[40,76],"better":[41],"to":[42,60,75,78,85,112],"use":[43],"noise":[49,97],"model":[52],"and":[53],"subtract":[54],"from":[56],"observation":[59],"form":[61],"an":[62,82,95,102],"indirect":[63],"speech.":[67],"Interestingly,":[68],"for":[69],"VTS,":[70],"this":[71,99],"methodology":[72,100],"turns":[73],"out":[74],"related":[77],"application":[80],"SNR-dependent":[83],"gain":[84],"direct":[87],"VTS":[88],"estimate.":[90],"In":[91],"results":[92],"obtained":[93],"on":[94],"automotive":[96],"task,":[98],"produces":[101],"average":[103],"improvement":[104],"1.6":[106],"dB":[107],"signal-to-noise":[108],"ratio":[109],"(SNR),":[110],"relative":[111],"conventional":[113],"methods.":[114]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}