{"id":"https://openalex.org/W1964723688","doi":"https://doi.org/10.1109/iscslp.2012.6423514","title":"TDOA information based vad for robust speech recognition in directional and diffuse noise field","display_name":"TDOA information based vad for robust speech recognition in directional and diffuse noise field","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1964723688","doi":"https://doi.org/10.1109/iscslp.2012.6423514","mag":"1964723688"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","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/A5018512814","display_name":"Kuan-Lang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Lang Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan","Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan 300, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan 300, R.O.C","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088864528","display_name":"Tai-Shih Chi","orcid":"https://orcid.org/0000-0002-0584-8399"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Shih Chi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan","Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan 300, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan 300, R.O.C","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05103396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"130"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9972000122070312,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"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/multilateration","display_name":"Multilateration","score":0.8779109716415405},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7283320426940918},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6874314546585083},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.6594310998916626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6528825163841248},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5911381244659424},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5456756353378296},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.45557087659835815},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44798898696899414},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.41067203879356384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4104359447956085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3645433783531189},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.31684574484825134},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15758588910102844},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13932570815086365},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07684209942817688}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.8779109716415405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283320426940918},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6874314546585083},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.6594310998916626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6528825163841248},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5911381244659424},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5456756353378296},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.45557087659835815},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44798898696899414},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.41067203879356384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4104359447956085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3645433783531189},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.31684574484825134},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15758588910102844},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13932570815086365},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07684209942817688},{"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.47999998927116394}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W56892040","https://openalex.org/W58061406","https://openalex.org/W169229064","https://openalex.org/W1586342741","https://openalex.org/W1931312565","https://openalex.org/W1973746598","https://openalex.org/W2017452035","https://openalex.org/W2034040413","https://openalex.org/W2041733487","https://openalex.org/W2086139506","https://openalex.org/W2099655464","https://openalex.org/W2116520137","https://openalex.org/W2149693148","https://openalex.org/W2151484683","https://openalex.org/W4285719527","https://openalex.org/W6602323980"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2188292175","https://openalex.org/W2385053527","https://openalex.org/W1983991597","https://openalex.org/W4386900535","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264"],"abstract_inverted_index":{"A":[0],"two-microphone":[1],"algorithm":[2,25,54],"is":[3,15,55],"proposed":[4,53,81],"to":[5,33,45],"improve":[6],"automatic":[7],"speech":[8,14],"recognition":[9,85,98],"(ASR)":[10],"rates":[11,60,86,99],"when":[12,87,100],"target":[13],"corrupted":[16],"by":[17],"directional":[18,35,68,90],"interferences":[19,36],"and":[20,37,70,92,95],"diffuse":[21,47,71,101],"noise":[22,102],"simultaneously.":[23],"The":[24],"adopts":[26],"the":[27,52,75,80],"time":[28],"difference":[29,77],"of":[30],"arrival":[31],"(TDOA)":[32],"suppress":[34,46],"a":[38,62,67,89],"TDOA-information":[39],"based":[40],"voice":[41],"activity":[42],"detector":[43],"(VAD)":[44],"noise.":[48,72],"Simulation":[49],"results":[50],"show":[51],"effective":[56],"in":[57,61],"improving":[58],"ASR":[59],"sound":[63],"field":[64],"mixed":[65],"with":[66,74],"interference":[69,91],"Compared":[73],"phase":[76],"(PD)":[78],"algorithm,":[79],"method":[82],"gives":[83],"comparable":[84],"facing":[88],"much":[93],"higher":[94],"more":[96],"robust":[97],"emerges.":[103]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
