{"id":"https://openalex.org/W1925904797","doi":"https://doi.org/10.21437/interspeech.2010-192","title":"Bimodal coherence based scale ambiguity cancellation for target speech extraction and enhancement","display_name":"Bimodal coherence based scale ambiguity cancellation for target speech extraction and enhancement","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W1925904797","doi":"https://doi.org/10.21437/interspeech.2010-192","mag":"1925904797"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-192","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5074138677","display_name":"Qingju Liu","orcid":"https://orcid.org/0000-0003-2288-3417"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Qingju Liu","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip Jackson","raw_affiliation_strings":["#N#University of Surrey#N#"],"affiliations":[{"raw_affiliation_string":"#N#University of Surrey#N#","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074138677"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.0145,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74171218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"438","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","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/T11447","display_name":"Blind Source Separation Techniques","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/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":0.9916999936103821,"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/computer-science","display_name":"Computer science","score":0.7476828694343567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6825214624404907},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6179371476173401},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6103124022483826},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6083441376686096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4802537262439728},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4739130735397339},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4723281264305115},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.467671275138855},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4292328655719757},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3424757719039917},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14134272933006287},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12939390540122986},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12288865447044373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476828694343567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6825214624404907},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6179371476173401},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6103124022483826},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6083441376686096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4802537262439728},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4739130735397339},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4723281264305115},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.467671275138855},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4292328655719757},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3424757719039917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14134272933006287},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12939390540122986},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12288865447044373},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2010-192","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.705.5281","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.705.5281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://personal.ee.surrey.ac.uk/Personal/W.Wang/papers/LiuWJ_INTERSPEECH_2010.pdf","raw_type":"text"},{"id":"pmh:oai:epubs.surrey.ac.uk:7725","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/7725/4/licence.txt","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"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":[{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5109756092","display_name":"Multi-Modal Blind Source Separation for Robot Audition","funder_award_id":"EP/H012842/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1527240141","https://openalex.org/W1787078711","https://openalex.org/W2096855653","https://openalex.org/W2099741732","https://openalex.org/W2132877328","https://openalex.org/W2135081730","https://openalex.org/W2142352693","https://openalex.org/W2154151281","https://openalex.org/W3031363333"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W1992295166","https://openalex.org/W2143508933","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743","https://openalex.org/W111365173"],"abstract_inverted_index":{"We":[0,39,63],"present":[1],"a":[2,20],"novel":[3],"method":[4],"for":[5],"extracting":[6],"target":[7],"speech":[8,93],"from":[9,35],"au-ditory":[10],"mixtures":[11],"using":[12,30,46],"bimodal":[13,48,95],"coherence,":[14,96],"which":[15],"is":[16],"statistically":[17],"characterised":[18],"by":[19],"Gaussian":[21,98],"mixture":[22,99],"modal":[23],"(GMM)":[24],"in":[25,50,59,82],"the":[26,31,36,42,47,51,56,68,72,75],"off-line":[27],"training":[28],"process,":[29],"robust":[32],"features":[33],"obtained":[34],"audio-visual":[37],"speech.":[38],"then":[40],"adjust":[41],"ICA-separated":[43],"spectral":[44],"components":[45],"coherence":[49],"time-frequency":[52],"domain,":[53],"to":[54,86],"mitigate":[55],"scale":[57],"ambiguities":[58],"different":[60],"frequency":[61],"bins.":[62],"tested":[64],"our":[65,79],"algorithm":[66,81],"on":[67],"XM2VTS":[69],"database,":[70],"and":[71],"results":[73],"show":[74],"performance":[76],"improvement":[77],"with":[78],"pro-posed":[80],"terms":[83],"of":[84],"signal":[85],"interference":[87],"ratio":[88],"(SIR)":[89],"measurements.":[90],"Index":[91],"Terms:":[92],"extraction,":[94],"audio-visual,":[97],"model":[100],"(GMM),":[101],"independent":[102],"compo-":[103]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}