{"id":"https://openalex.org/W2040293000","doi":"https://doi.org/10.1109/icmlc.2014.7009663","title":"Fast HMM-driven beamforming for robust speech recognition in reverberant environments","display_name":"Fast HMM-driven beamforming for robust speech recognition in reverberant environments","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2040293000","doi":"https://doi.org/10.1109/icmlc.2014.7009663","mag":"2040293000"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc.2014.7009663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2014.7009663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Machine Learning and Cybernetics","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":0.10773668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"529","last_page":"532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9861000180244446,"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/reverberation","display_name":"Reverberation","score":0.8147107362747192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.762205958366394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7507038116455078},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7419643998146057},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5690838694572449},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.47925353050231934},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4417894184589386},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4262595772743225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3838808536529541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3274097442626953},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2767565846443176},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20303311944007874},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17603090405464172},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08922514319419861},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.08048170804977417}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8147107362747192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762205958366394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7507038116455078},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7419643998146057},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5690838694572449},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.47925353050231934},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4417894184589386},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4262595772743225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3838808536529541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3274097442626953},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2767565846443176},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20303311944007874},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17603090405464172},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08922514319419861},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.08048170804977417},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc.2014.7009663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2014.7009663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Machine Learning and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W14578209","https://openalex.org/W161419836","https://openalex.org/W1573570773","https://openalex.org/W2137401359","https://openalex.org/W2151046798","https://openalex.org/W2245569228","https://openalex.org/W2272141078","https://openalex.org/W3022446722","https://openalex.org/W4206633762","https://openalex.org/W6606545873","https://openalex.org/W6634340323","https://openalex.org/W6680646222","https://openalex.org/W6690610466","https://openalex.org/W6776589058"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W4401069787","https://openalex.org/W1499578372","https://openalex.org/W2368849850"],"abstract_inverted_index":{"The":[0,86],"reverberation":[1,17,51,98],"is":[2,18,89],"induced":[3],"from":[4],"the":[5,8,16,22,31,50,55,80,92,95,112,115,122,131,140,144],"combination":[6],"of":[7,33,57,61,76,82,94,105,114,134],"direct":[9],"waveform":[10],"and":[11],"multiple":[12],"reflected":[13],"waveforms.":[14],"Therefore,":[15],"highly":[19],"corrected":[20],"with":[21,63],"original":[23,83],"speech":[24,34,102,148],"signal.":[25],"This":[26,36,66],"leads":[27],"to":[28,41,70,110],"dramatically":[29],"degrade":[30],"performance":[32,113],"recognition.":[35],"paper":[37],"extends":[38],"VTS":[39,64],"methodology":[40],"develop":[42],"a":[43,72],"robust":[44,147],"technique":[45],"for":[46,91,130],"HMM-driven":[47,84,135],"beamformer":[48,77],"on":[49,127,150],"environments.":[52],"We":[53],"approximate":[54],"logarithm":[56],"Gaussian":[58],"mixture":[59],"models":[60],"HMM":[62],"expansion.":[65],"makes":[67],"it":[68],"possible":[69],"obtain":[71],"simpler":[73],"updating":[74],"functions":[75],"parameters":[78],"than":[79],"counterparts":[81],"beamformer.":[85,136],"RWCP":[87],"database":[88],"used":[90],"simulation":[93],"multi-channel":[96],"recorded":[97],"speech.":[99],"A":[100],"speaker-independent":[101],"query":[103],"task":[104],"Mandarin":[106],"names":[107],"was":[108,125],"applied":[109],"evaluate":[111],"beamformers.":[116],"Our":[117],"experimental":[118],"results":[119],"show":[120],"that":[121,139],"proposed":[123,141],"algorithm":[124],"effective":[126],"compoutation":[128],"reduction":[129],"adaptation":[132],"process":[133],"It":[137],"indicates":[138],"framework":[142],"benefits":[143],"development":[145],"in":[146],"recognition":[149],"resource-constrained":[151],"platforms.":[152]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}