{"id":"https://openalex.org/W3176255527","doi":"https://doi.org/10.1109/iscslp.2014.6936613","title":"Single-channel dereverberation for distant-talking speech recognition by combining denoising autoencoder and temporal structure normalization","display_name":"Single-channel dereverberation for distant-talking speech recognition by combining denoising autoencoder and temporal structure normalization","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W3176255527","doi":"https://doi.org/10.1109/iscslp.2014.6936613","mag":"3176255527"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th 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/A5100901893","display_name":"Yuma Ueda","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuma Ueda","raw_affiliation_strings":["Graduate School of Engineering, Shizuoka University, Hamamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Shizuoka University, Hamamatsu, Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]},{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Nagaoka University of Technology, Nagaoka, Japan"],"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Nagaoka, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071123569","display_name":"Atsuhiko Kai","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuhiko Kai","raw_affiliation_strings":["Graduate School of Engineering, Shizuoka University, Hamamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Shizuoka University, Hamamatsu, Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Human Language Technology, Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Human Language Technology, Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100901893"],"corresponding_institution_ids":["https://openalex.org/I1298590031"],"apc_list":null,"apc_paid":null,"fwci":0.8734,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77256944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"379","last_page":"383"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9965999722480774,"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/normalization","display_name":"Normalization (sociology)","score":0.8555240035057068},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7576732039451599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.698399543762207},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6894965171813965},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6700687408447266},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6242863535881042},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5751361846923828},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47656014561653137},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.47104716300964355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.467923641204834},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45899254083633423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4464339017868042},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4309846758842468},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34523072838783264},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2096812129020691},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12554913759231567},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06083688139915466}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8555240035057068},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7576732039451599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698399543762207},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6894965171813965},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6700687408447266},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6242863535881042},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5751361846923828},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47656014561653137},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.47104716300964355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.467923641204834},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45899254083633423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4464339017868042},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4309846758842468},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34523072838783264},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2096812129020691},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12554913759231567},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06083688139915466},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W177307080","https://openalex.org/W1973669708","https://openalex.org/W1982846521","https://openalex.org/W1989314204","https://openalex.org/W1992713442","https://openalex.org/W1998229164","https://openalex.org/W2005522781","https://openalex.org/W2009106392","https://openalex.org/W2026136559","https://openalex.org/W2037740282","https://openalex.org/W2047769394","https://openalex.org/W2053150333","https://openalex.org/W2069976350","https://openalex.org/W2092305100","https://openalex.org/W2100495367","https://openalex.org/W2103564015","https://openalex.org/W2110322414","https://openalex.org/W2112748425","https://openalex.org/W2114782757","https://openalex.org/W2115515280","https://openalex.org/W2128653836","https://openalex.org/W2130722890","https://openalex.org/W2132054610","https://openalex.org/W2132214945","https://openalex.org/W2142117481","https://openalex.org/W2145094598","https://openalex.org/W2147166770","https://openalex.org/W2148898720","https://openalex.org/W2151435578","https://openalex.org/W2296581541","https://openalex.org/W2402919203","https://openalex.org/W2405774341","https://openalex.org/W2997574889","https://openalex.org/W3186851455","https://openalex.org/W6647660671","https://openalex.org/W6656840252","https://openalex.org/W6676279616","https://openalex.org/W6681096077","https://openalex.org/W6681171195","https://openalex.org/W6697251715","https://openalex.org/W6713521420","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W1978230699","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2069431997","https://openalex.org/W4385672897","https://openalex.org/W2352700476","https://openalex.org/W106160982","https://openalex.org/W2359140082"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,40],"propose":[4],"a":[5,29,42,85],"robust":[6],"distant-talking":[7],"speech":[8,36,76],"recognition":[9],"by":[10,59],"combining":[11,84],"cepstral":[12,33],"domain":[13,34],"denoising":[14],"autoencoder":[15],"(DAE)":[16],"and":[17,56,79,88,109],"temporal":[18,47],"structure":[19,48],"normalization":[20,49],"(TSN)":[21,50],"filter.":[22],"For":[23],"the":[24,32,54,61,90,101],"proposed":[25,71],"method,":[26],"after":[27],"applying":[28],"DAE":[30,87],"in":[31,77,106,114],"of":[35,67,100],"to":[37,52,64,104,112],"suppress":[38],"reverberation,":[39],"apply":[41],"post-processing":[43],"technology":[44],"based":[45],"on":[46],"filter":[51],"reduce":[53],"noise":[55],"reverberation":[57],"effects":[58],"normalizing":[60],"modulation":[62],"spectra":[63,66],"reference":[65],"clean":[68],"speech.":[69],"The":[70],"method":[72],"was":[73,96],"evaluated":[74],"using":[75],"simulated":[78,107],"real":[80,115],"reverberant":[81],"environments.":[82],"By":[83],"cepstral-domain":[86],"TSN,":[89],"average":[91],"Word":[92],"Error":[93],"Rate":[94],"(WER)":[95],"reduced":[97],"from":[98,110],"25.2%":[99],"baseline":[102],"system":[103],"21.2%":[105],"environments":[108],"47.5%":[111],"41.3%":[113],"environments,":[116],"respectively.":[117]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}