{"id":"https://openalex.org/W2122807390","doi":"https://doi.org/10.1109/icme.2005.1521611","title":"Multi-Sensory Speech Processing: Incorporating Automatically Extracted Hidden Dynamic Information","display_name":"Multi-Sensory Speech Processing: Incorporating Automatically Extracted Hidden Dynamic Information","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2122807390","doi":"https://doi.org/10.1109/icme.2005.1521611","mag":"2122807390"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","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/A5110262793","display_name":"A. Subramanya","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"A. Subramanya","raw_affiliation_strings":["SSLI Lab, University of Washington, Seattle, WA, USA","SSLI Lab, Washington Univ., Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"SSLI Lab, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"SSLI Lab, Washington Univ., Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320723","display_name":"Zhiyuan Liu","orcid":"https://orcid.org/0000-0002-7709-2543"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Zicheng Liu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056480447","display_name":"Zheng Zhang","orcid":"https://orcid.org/0009-0003-2344-8158"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Zhengyou Zhang","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110262793"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.20909641,"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":"1074","last_page":"1077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9954000115394592,"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":0.9606000185012817,"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/formant","display_name":"Formant","score":0.8190057277679443},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8058853149414062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7490509748458862},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5867823362350464},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5602777600288391},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5536646246910095},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48167693614959717},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4654890298843384},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44811564683914185},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44330811500549316},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4421076476573944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3773551285266876},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2353183925151825},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.09395614266395569},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.06825610995292664},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06679496169090271}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8190057277679443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058853149414062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7490509748458862},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5867823362350464},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5602777600288391},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5536646246910095},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48167693614959717},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4654890298843384},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44811564683914185},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44330811500549316},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4421076476573944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3773551285266876},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2353183925151825},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.09395614266395569},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.06825610995292664},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06679496169090271},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2005.1521611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.5238","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.5238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/~zliu/icme-li-cr1597.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1560505509","https://openalex.org/W2118329604","https://openalex.org/W2128127640","https://openalex.org/W2153367543","https://openalex.org/W2160450507","https://openalex.org/W2163039187","https://openalex.org/W2165544306","https://openalex.org/W4230621721","https://openalex.org/W6678978470","https://openalex.org/W6684010711"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2089240210","https://openalex.org/W642007152"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2],"novel":[3],"technique":[4,83],"for":[5,9,14,84,117],"multi-sensory":[6],"speech":[7,12,17,28,42,86,110,119],"processing":[8],"enhancing":[10],"noisy":[11,118],"and":[13,21,58],"improved":[15,82,115],"noise-robust":[16],"recognition.":[18,120],"Both":[19],"air-":[20],"bone-conductive":[22],"microphones":[23],"are":[24],"used":[25],"to":[26],"capture":[27],"data":[29,111],"where":[30],"the":[31,44,52,69,75,90,96,107],"bone":[32],"sensor":[33],"contains":[34],"virtually":[35],"noise-free":[36],"hidden":[37],"dynamic":[38],"information":[39,73],"of":[40,46,68],"clean":[41],"in":[43,51],"form":[45],"formant":[47,72,97],"trajectories.":[48,98],"The":[49],"distortion":[50],"bone-sensor":[53,76],"signal":[54,102],"such":[55],"as":[56],"teeth-clacking":[57],"noise":[59],"leakage":[60],"can":[61],"be":[62],"effectively":[63],"removed":[64],"by":[65],"making":[66],"use":[67],"automatically":[70],"extracted":[71],"from":[74,95],"signal.":[77],"This":[78],"paper":[79],"reports":[80],"an":[81],"synthesizing":[85],"waveforms":[87],"based":[88],"on":[89],"LPC":[91],"cepstra":[92],"computed":[93],"analytically":[94],"When":[99],"this":[100],"new":[101],"stream":[103],"is":[104],"fused":[105],"with":[106],"other":[108],"available":[109],"streams,":[112],"we":[113],"achieved":[114],"performance":[116]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}