{"id":"https://openalex.org/W2166043648","doi":"https://doi.org/10.1109/icassp.2005.1415168","title":"Two-stage Noise Spectra Estimation and Regression based In-car Speech Recognition using Single Distant Microphone","display_name":"Two-stage Noise Spectra Estimation and Regression based In-car Speech Recognition using Single Distant Microphone","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2166043648","doi":"https://doi.org/10.1109/icassp.2005.1415168","mag":"2166043648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5008726578","display_name":"Weifeng Li","orcid":"https://orcid.org/0000-0002-2105-3596"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Weifeng Li","raw_affiliation_strings":["Graduate School of Engineering, University of Nagoya, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, University of Nagoya, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111495545","display_name":"K. Itou","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Itou","raw_affiliation_strings":["Graduate School of Information Science, University of Nagoya, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, University of Nagoya, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Takeda","raw_affiliation_strings":["Graduate School of Information Science, University of Nagoya, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, University of Nagoya, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021756192","display_name":"Fumitada Itakura","orcid":null},"institutions":[{"id":"https://openalex.org/I96636082","display_name":"Meijo University","ror":"https://ror.org/04h42fc75","country_code":"JP","type":"education","lineage":["https://openalex.org/I96636082"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"F. Itakura","raw_affiliation_strings":["Faculty of Science and Technology, Meijo University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Science and Technology, Meijo University, Nagoya, Japan","institution_ids":["https://openalex.org/I96636082"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008726578"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":1.9081,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8624141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"533","last_page":"536"},"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":0.9980999827384949,"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":0.9965000152587891,"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/speech-recognition","display_name":"Speech recognition","score":0.6690616607666016},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6679749488830566},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6448506712913513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5970187783241272},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5935165286064148},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5332920551300049},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4935818910598755},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.492390513420105},{"id":"https://openalex.org/keywords/value-noise","display_name":"Value noise","score":0.4738999903202057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46873292326927185},{"id":"https://openalex.org/keywords/gradient-noise","display_name":"Gradient noise","score":0.4291793704032898},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.4231749475002289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38558363914489746},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3333340883255005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3123995065689087},{"id":"https://openalex.org/keywords/noise-floor","display_name":"Noise floor","score":0.20324492454528809},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.1804291009902954}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6690616607666016},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6679749488830566},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6448506712913513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5970187783241272},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5935165286064148},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5332920551300049},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4935818910598755},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.492390513420105},{"id":"https://openalex.org/C182163834","wikidata":"https://www.wikidata.org/wiki/Q2926529","display_name":"Value noise","level":5,"score":0.4738999903202057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46873292326927185},{"id":"https://openalex.org/C200378446","wikidata":"https://www.wikidata.org/wiki/Q4147391","display_name":"Gradient noise","level":5,"score":0.4291793704032898},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.4231749475002289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38558363914489746},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3333340883255005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3123995065689087},{"id":"https://openalex.org/C187612029","wikidata":"https://www.wikidata.org/wiki/Q17083130","display_name":"Noise floor","level":4,"score":0.20324492454528809},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.1804291009902954},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1645939","https://openalex.org/W1585333835","https://openalex.org/W1687555731","https://openalex.org/W1888374534","https://openalex.org/W1985090574","https://openalex.org/W2021416479","https://openalex.org/W2038054257","https://openalex.org/W2105393299","https://openalex.org/W2121973264","https://openalex.org/W2124776405","https://openalex.org/W2125630648","https://openalex.org/W2146324387","https://openalex.org/W2158336491","https://openalex.org/W2164010719","https://openalex.org/W2169399159","https://openalex.org/W3147539069","https://openalex.org/W6635229333","https://openalex.org/W6646555135","https://openalex.org/W6679009796"],"related_works":["https://openalex.org/W2053318377","https://openalex.org/W3125397569","https://openalex.org/W2027616686","https://openalex.org/W4312849460","https://openalex.org/W2401089611","https://openalex.org/W2120405331","https://openalex.org/W2394151061","https://openalex.org/W2200053498","https://openalex.org/W4226451553","https://openalex.org/W2055472139"],"abstract_inverted_index":{"We":[0,38],"present":[1],"a":[2,30,32,41],"two-stage":[3,66],"noise":[4,11,24,35,54,67,78],"spectra":[5],"estimation":[6,12,25,68,73],"approach.":[7],"After":[8],"the":[9,14,22,48,52,56,64,82,86],"first-stage":[10],"using":[13],"improved":[15],"minima":[16],"controlled":[17],"recursive":[18],"averaging":[19],"(IMCRA)":[20],"method,":[21],"second-stage":[23],"is":[26],"performed":[27],"by":[28,46],"employing":[29],"maximum":[31],"posteriori":[33],"(MAP)":[34],"amplitude":[36],"estimator.":[37],"also":[39],"develop":[40],"regression-based":[42,88],"speech":[43,50],"enhancement":[44],"system":[45],"approximating":[47],"clean":[49],"with":[51],"estimated":[53],"and":[55],"original":[57,83],"noisy":[58,84],"speech.":[59],"Evaluation":[60],"experiments":[61,106],"show":[62],"that":[63],"proposed":[65,87],"method":[69],"results":[70],"in":[71,101,108],"lower":[72],"error":[74,95],"for":[75],"all":[76],"test":[77],"types.":[79],"Compared":[80],"to":[81],"speech,":[85],"approach":[89],"obtains":[90],"an":[91],"average":[92],"relative":[93],"word":[94,104],"rate":[96],"(WER)":[97],"reduction":[98],"of":[99],"65%":[100],"our":[102],"isolated":[103],"recognition":[105],"conducted":[107],"12":[109],"real":[110],"car":[111],"environments.":[112]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}