{"id":"https://openalex.org/W1981152367","doi":"https://doi.org/10.1109/fskd.2012.6234339","title":"Leveraging gain normalization for sub-band temporal features in noise-robust speech recognition","display_name":"Leveraging gain normalization for sub-band temporal features in noise-robust speech recognition","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W1981152367","doi":"https://doi.org/10.1109/fskd.2012.6234339","mag":"1981152367"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2012.6234339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6234339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","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/A5000054510","display_name":"Hao-teng Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hao-Teng Fan","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","[Department of Electrical Engineering, National Chi-Nan University, Nantou, Taiwan]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"[Department of Electrical Engineering, National Chi-Nan University, Nantou, Taiwan]","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-weih Hung","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","[Department of Electrical Engineering, National Chi-Nan University, Nantou, Taiwan]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"[Department of Electrical Engineering, National Chi-Nan University, Nantou, Taiwan]","institution_ids":["https://openalex.org/I193365169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000054510"],"corresponding_institution_ids":["https://openalex.org/I193365169"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06492672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"1409","last_page":"1412"},"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":0.9991000294685364,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7574173212051392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7098298668861389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5624581575393677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5616494417190552},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5560144186019897},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.5441310405731201},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5418092012405396},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.46664029359817505},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.42182207107543945},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38120248913764954},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.3609187602996826}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7574173212051392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098298668861389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5624581575393677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5616494417190552},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5560144186019897},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.5441310405731201},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5418092012405396},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.46664029359817505},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.42182207107543945},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38120248913764954},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.3609187602996826},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/fskd.2012.6234339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6234339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320323837","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W90966543","https://openalex.org/W96504731","https://openalex.org/W97348585","https://openalex.org/W319849403","https://openalex.org/W1535749512","https://openalex.org/W1963881067","https://openalex.org/W2050693797","https://openalex.org/W2105885996","https://openalex.org/W2151484683","https://openalex.org/W2155082225","https://openalex.org/W2172200851","https://openalex.org/W6603749997","https://openalex.org/W6603921909","https://openalex.org/W6603922934","https://openalex.org/W6641145148","https://openalex.org/W6685110083"],"related_works":["https://openalex.org/W4252379076","https://openalex.org/W2085792030","https://openalex.org/W2030316446","https://openalex.org/W1588899229","https://openalex.org/W2172291505","https://openalex.org/W2023142747","https://openalex.org/W2037009764","https://openalex.org/W2063036707","https://openalex.org/W2501033992","https://openalex.org/W2377605153"],"abstract_inverted_index":{"In":[0,26,97],"this":[1,103],"paper,":[2],"we":[3,30],"propose":[4],"to":[5,34,93],"operate":[6],"the":[7,16,27,32,36,44,53,60,69,76,80,86,98,108,112],"sub-band":[8,49,65,87,105],"division":[9],"via":[10],"discrete":[11],"wavelet":[12],"transform":[13],"(DWT)":[14],"before":[15],"process":[17,72,110],"of":[18,63],"gain":[19,45,70],"normalization":[20,46,71],"(GN)":[21],"in":[22,120],"producing":[23],"speech":[24],"features.":[25],"presented":[28,81],"approach,":[29],"apply":[31],"DWT":[33,62],"decompose":[35],"temporal-domain":[37],"cepstral":[38],"feature":[39,50,55],"sequence,":[40],"and":[41,90,101,111,118],"then":[42],"perform":[43],"on":[47,75],"each":[48],"stream.":[51],"Finally,":[52],"new":[54,104],"stream":[56],"is":[57,91],"obtained":[58],"by":[59,116],"inverse":[61],"all":[64],"streams.":[66],"Compared":[67],"with":[68,85],"directly":[73],"performed":[74],"original":[77,113],"full-band":[78,114],"stream,":[79],"approach":[82],"can":[83],"deal":[84],"distortions":[88],"individually":[89],"expected":[92],"be":[94],"more":[95],"noise-robust.":[96],"Aurora-2":[99],"database":[100],"task,":[102],"GN":[106,115],"outperforms":[107],"baseline":[109],"65.51%":[117],"18.20%":[119],"relative":[121],"word":[122],"error":[123],"reduction.":[124]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}