{"id":"https://openalex.org/W2185164075","doi":"https://doi.org/10.1109/icmlc.2015.7340618","title":"HCRF-driven beamforming for reverberant speech recognition","display_name":"HCRF-driven beamforming for reverberant speech recognition","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W2185164075","doi":"https://doi.org/10.1109/icmlc.2015.7340618","mag":"2185164075"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc.2015.7340618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2015.7340618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Machine Learning and Cybernetics (ICMLC)","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/A5027076173","display_name":"Wei\u2010Tyng Hong","orcid":"https://orcid.org/0000-0003-1177-459X"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Wei-Tyng Hong","raw_affiliation_strings":["Department of Communications Engineering Yuan Ze University, Taiwan","Department of Communications Engineering, Yuan Ze University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering Yuan Ze University, Taiwan","institution_ids":["https://openalex.org/I99908691"]},{"raw_affiliation_string":"Department of Communications Engineering, Yuan Ze University, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027076173"],"corresponding_institution_ids":["https://openalex.org/I99908691"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10529384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"578","last_page":"581"},"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":0.9966999888420105,"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":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.9110869765281677},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7894382476806641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7645966410636902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7630081176757812},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.7007416486740112},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6868377327919006},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.4565316438674927},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.4500308036804199},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44228124618530273},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41660866141319275},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4165796935558319},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3805561661720276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09913516044616699},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09374526143074036},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06848376989364624}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9110869765281677},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7894382476806641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645966410636902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7630081176757812},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7007416486740112},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6868377327919006},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.4565316438674927},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.4500308036804199},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44228124618530273},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41660866141319275},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4165796935558319},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3805561661720276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09913516044616699},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09374526143074036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06848376989364624},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc.2015.7340618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2015.7340618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Machine Learning and Cybernetics (ICMLC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W2101534792","https://openalex.org/W2131646590","https://openalex.org/W2151046798","https://openalex.org/W2245569228","https://openalex.org/W2272141078","https://openalex.org/W3022446722","https://openalex.org/W4206633762","https://openalex.org/W6690610466","https://openalex.org/W6693924657","https://openalex.org/W6776589058","https://openalex.org/W6807036708"],"related_works":["https://openalex.org/W4389082013","https://openalex.org/W2767070583","https://openalex.org/W2380771148","https://openalex.org/W2109356272","https://openalex.org/W2132495960","https://openalex.org/W2389562147","https://openalex.org/W2538903081","https://openalex.org/W4386746628","https://openalex.org/W1982764159","https://openalex.org/W2348931051"],"abstract_inverted_index":{"Reverberation":[0],"effects":[1],"dramatically":[2],"degrade":[3],"the":[4,14,22,26,34,41,46,68,72,77,84,88,91,97,103,117,121],"performance":[5],"of":[6,48,54,74,79,105,124],"automatic":[7],"speech":[8,28],"recognition":[9],"(ASR).":[10],"In":[11,38,56],"conventional":[12],"approaches,":[13],"microphone":[15,107],"array-based":[16,49],"beamformers":[17],"try":[18],"to":[19,100],"filter":[20],"rout":[21],"reverberation":[23],"and":[24,51,76,90],"re-build":[25],"enhanced":[27],"signals":[29],"for":[30,64],"ASR":[31,85,92],"based":[32,82],"on":[33,83],"SSR":[35],"(signal-to-reverberation)":[36],"criterion.":[37],"such":[39],"approach,":[40],"inconsistent":[42],"criterions":[43],"exists":[44],"between":[45],"operation":[47],"beamforming":[50],"model":[52],"training":[53],"ASR.":[55],"this":[57],"study,":[58],"we":[59],"propose":[60],"a":[61],"HCRF-driven":[62],"approach":[63],"beamformer":[65,80],"in":[66],"which":[67],"acoustic":[69],"models":[70,89],"employ":[71],"framework":[73],"HCRFs":[75],"adaptation":[78,98],"is":[81,114],"output":[86],"Both":[87],"result":[93],"are":[94],"incorporated":[95],"into":[96],"process":[99],"iteratively":[101],"estimate":[102],"parameters":[104],"an":[106],"array.":[108],"A":[109],"significant":[110],"error":[111],"rate":[112],"reduction":[113],"obtained":[115],"by":[116],"proposed":[118],"method":[119],"through":[120],"experimental":[122],"results":[123],"RWCP":[125],"room":[126],"impulse":[127],"database.":[128]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}