{"id":"https://openalex.org/W2107947019","doi":"https://doi.org/10.1109/icassp.2009.4960648","title":"Temporal contrast normalization and edge-preserved smoothing on temporal modulation structure for robust speech recognition","display_name":"Temporal contrast normalization and edge-preserved smoothing on temporal modulation structure for robust speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2107947019","doi":"https://doi.org/10.1109/icassp.2009.4960648","mag":"2107947019"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal 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/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"X. Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","ATR-SLC, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"ATR-SLC, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077037266","display_name":"Shigeki Matsuda","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Matsuda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","ATR-SLC, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"ATR-SLC, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Unoki","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Japan","Japan Advanced Institute of Science and Technology, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Japan#TAB#","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026797033","display_name":"Tadaaki Shimizu","orcid":"https://orcid.org/0000-0002-8606-8721"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Shimizu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","ATR-SLC, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"ATR-SLC, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081081128","display_name":"Satoru Nakamura","orcid":"https://orcid.org/0000-0001-8245-7925"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Nakamura","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","ATR-SLC, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"ATR-SLC, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034792613"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":1.4099,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80909214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"270","issue":null,"first_page":"4573","last_page":"4576"},"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":0.9988999962806702,"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":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7742990255355835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6332740783691406},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6172332763671875},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5390943288803101},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5371770262718201},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5022256374359131},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4877665638923645},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.482086718082428},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4607715308666229},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.44560232758522034},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3853261172771454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35956770181655884},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14386966824531555},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08775165677070618},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0628768801689148}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7742990255355835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6332740783691406},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6172332763671875},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5390943288803101},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5371770262718201},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5022256374359131},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4877665638923645},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.482086718082428},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4607715308666229},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.44560232758522034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3853261172771454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35956770181655884},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14386966824531555},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08775165677070618},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0628768801689148},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1974932989","https://openalex.org/W2054392851","https://openalex.org/W2075012882","https://openalex.org/W2092305100","https://openalex.org/W2103253424","https://openalex.org/W2109991658","https://openalex.org/W2150764838","https://openalex.org/W4245919820","https://openalex.org/W6675639387"],"related_works":["https://openalex.org/W203970584","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2401089611","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2962707588","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,102,120],"two-step":[6],"processing":[7,30,53],"algorithm":[8,79,130,138],"which":[9],"adaptively":[10],"normalizes":[11],"the":[12,34,40,57,64,71,125,137],"temporal":[13,35,59],"modulation":[14,36,60,73],"of":[15,39,95],"speech":[16,20,24,72,81,97],"to":[17,32,55,62,67],"extract":[18],"robust":[19],"feature":[21],"for":[22,44,141,152,157,163,167,170,177,181,194],"automatic":[23],"recognition":[25,82],"systems.":[26],"The":[27,50],"first":[28],"step":[29,52],"is":[31,54],"normalize":[33],"contrast":[37],"(TMC)":[38],"cepstral":[41],"time":[42],"series":[43],"both":[45,111,185],"clean":[46,96,153],"and":[47,107,113,159,179,187],"noisy":[48,108,182],"speech.":[49],"second":[51],"smooth":[56],"normalized":[58],"structure":[61],"reduce":[63],"artifacts":[65],"due":[66],"noise":[68,86,92,115,118,143],"while":[69],"preserving":[70],"events":[74],"(edges).":[75],"We":[76],"tested":[77],"our":[78],"on":[80],"experiments":[83],"in":[84,119],"additive":[85,114,142,188],"condition":[87,93,109,183],"(AURORA-2J":[88],"data":[89],"corpus),":[90],"reverberant":[91,112,171,186],"(convolution":[94],"utterances":[98],"from":[99],"AURORA-2J":[100],"with":[101,110,184],"smart":[103,121],"room":[104],"impulse":[105],"response),":[106],"(air":[116],"conditioner":[117],"room).":[122],"For":[123],"comparison,":[124],"ETSI":[126],"advanced":[127],"front-end":[128],"(AFE)":[129],"was":[131],"used.":[132],"Our":[133],"results":[134],"showed":[135],"that":[136],"provided:":[139],"(1)":[140],"condition,":[144,172],"57.26%":[145],"relative":[146],"word":[147],"error":[148],"reduction":[149],"(RWER)":[150],"rate":[151,162,175,192],"conditional":[154],"training":[155,165],"(59.37%":[156],"AFE),":[158,168],"33.52%":[160],"RWER":[161,174,191],"multi-conditional":[164],"(35.77%":[166],"(2)":[169],"51.28%":[173],"(10.17%":[176],"AFE)":[178],"(3)":[180],"noise,":[189],"71.74%":[190],"(48.86%":[193],"AFE).":[195]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}