{"id":"https://openalex.org/W1491017269","doi":"https://doi.org/10.21437/interspeech.2008-290","title":"A posterior approach for microphone array based speech recognition","display_name":"A posterior approach for microphone array based speech recognition","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W1491017269","doi":"https://doi.org/10.21437/interspeech.2008-290","mag":"1491017269"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-290","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/3907","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100391414","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0001-6809-4988"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039529498","display_name":"Ivan Himawan","orcid":"https://orcid.org/0000-0003-3848-244X"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":["Queensland University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026893328","display_name":"Joe Frankel","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joe Frankel","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"996","last_page":"999"},"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":0.9968000054359436,"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/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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/beamforming","display_name":"Beamforming","score":0.8412983417510986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7873378992080688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7749950885772705},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.7740083932876587},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7321280241012573},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7011016607284546},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5512371063232422},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5092700719833374},{"id":"https://openalex.org/keywords/noise-canceling-microphone","display_name":"Noise-canceling microphone","score":0.48484790325164795},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47472628951072693},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4495217204093933},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4425402879714966},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44000983238220215},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4259988069534302},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.4155414402484894},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3512556552886963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29001182317733765},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12681838870048523},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12477803230285645}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.8412983417510986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7873378992080688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7749950885772705},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7740083932876587},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7321280241012573},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7011016607284546},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5512371063232422},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5092700719833374},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.48484790325164795},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47472628951072693},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4495217204093933},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4425402879714966},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44000983238220215},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4259988069534302},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.4155414402484894},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3512556552886963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29001182317733765},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12681838870048523},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12477803230285645},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":6,"locations":[{"id":"doi:10.21437/interspeech.2008-290","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/3907","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3907","pdf_url":"http://hdl.handle.net/1842/3907","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:pure.ed.ac.uk:publications/4b51e022-7f14-4929-9e13-e96bd4855b2e","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2008/i08_0996.html","pdf_url":"https://www.pure.ed.ac.uk/ws/files/8426354/A_posterior_approach_for_microphone_array_based_speech_recognition.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.217.1910","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.1910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/marray.a.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.qut.edu.au:15341","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 9th Annual Conference of the International Speech Communication Association (Interspeech 2008) incorporating the 12th Australasian International Conference on Speech Science and Technology (SST)","raw_type":"Chapter in Book, Report or Conference volume"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/4b51e022-7f14-4929-9e13-e96bd4855b2e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/4b51e022-7f14-4929-9e13-e96bd4855b2e","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, D, Himawan, I, Frankel, J & King, S 2008, A Posterior Approach for Microphone Array Based Speech Recognition. in Interspeech. pp. 996-999. < http://hdl.handle.net/1842/3907 >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3907","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3907","pdf_url":"http://hdl.handle.net/1842/3907","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1491017269.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W87586386","https://openalex.org/W159361053","https://openalex.org/W1488173215","https://openalex.org/W1540832706","https://openalex.org/W2027499299","https://openalex.org/W2046317813","https://openalex.org/W2086040672","https://openalex.org/W2114044590","https://openalex.org/W2116623987","https://openalex.org/W2147166770","https://openalex.org/W2157774199","https://openalex.org/W2165712214","https://openalex.org/W2468573742"],"related_works":["https://openalex.org/W2122951924","https://openalex.org/W2092524451","https://openalex.org/W2109356272","https://openalex.org/W2348931051","https://openalex.org/W2385432413","https://openalex.org/W2389562147","https://openalex.org/W2132495960","https://openalex.org/W2379497378","https://openalex.org/W2135485548","https://openalex.org/W2251439150"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,85,90,133],"recognition":[2],"(ASR)":[3],"is":[4,119],"difficult":[5],"in":[6,29,100,126],"environments":[7],"such":[8,30],"as":[9],"multiparty":[10],"meetings":[11],"because":[12],"of":[13,49,88],"adverse":[14],"acoustic":[15],"conditions:":[16],"background":[17],"noise,":[18],"reverberation":[19],"and":[20,42,54,60,116],"cross-talk.":[21],"Microphone":[22],"arrays":[23],"can":[24],"increase":[25],"ASR":[26],"accuracy":[27],"dramatically":[28],"situations.":[31],"However,":[32],"most":[33],"existing":[34],"beamforming":[35,115,123],"techniques":[36],"use":[37],"time-domain":[38],"signal":[39],"processing":[40],"theory":[41],"are":[43,69,74,98],"based":[44],"on":[45],"a":[46,78,101,110,127],"geometric":[47,67],"analysis":[48],"the":[50,66],"relationship":[51],"between":[52],"sources":[53],"microphones.":[55],"This":[56],"limits":[57],"their":[58],"application,":[59],"leads":[61],"to":[62],"performance":[63],"degradation":[64],"when":[65],"properties":[68],"unavailable,":[70],"or":[71],"heterogeneous":[72],"channels":[73],"used.":[75],"We":[76],"present":[77],"new":[79],"posterior-based":[80],"approach":[81,139],"for":[82],"microphone":[83,135],"array":[84],"recognition.":[86],"Instead":[87],"enhancing":[89],"signals,":[91],"we":[92],"enhance":[93],"posterior":[94],"phone":[95],"probabilities":[96],"which":[97],"used":[99],"tandem":[102,138],"ANN-HMM":[103],"system.":[104],"Significant":[105],"improvements":[106],"were":[107],"achieved":[108],"over":[109],"single":[111],"channel":[112],"baseline.":[113],"Combining":[114],"our":[117],"method":[118],"significantly":[120],"better":[121],"than":[122],"alone,":[124],"especially":[125],"moving":[128],"speakers":[129],"scenario.":[130],"Index":[131],"Terms:":[132],"recognition,":[134],"array,":[136],"beamforming,":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}