{"id":"https://openalex.org/W198031547","doi":"https://doi.org/10.21437/icslp.2002-605","title":"Robust feature extraction in a variety of input devices on the basis of ETSI standard DSR front-end","display_name":"Robust feature extraction in a variety of input devices on the basis of ETSI standard DSR front-end","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W198031547","doi":"https://doi.org/10.21437/icslp.2002-605","mag":"198031547"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-605","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5113866096","display_name":"Satoru Tsuge","orcid":"https://orcid.org/0000-0002-3392-7852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoru Tsuge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112035972","display_name":"Shingo Kuroiwa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shingo Kuroiwa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109136046","display_name":"Masami Shishibori","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masami Shishibori","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071943346","display_name":"Fuji Ren","orcid":"https://orcid.org/0000-0003-4860-9184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuji Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101897942","display_name":"Kenji Kita","orcid":"https://orcid.org/0000-0003-3275-3667"},"institutions":[{"id":"https://openalex.org/I922474255","display_name":"Tokushima University","ror":"https://ror.org/044vy1d05","country_code":"JP","type":"education","lineage":["https://openalex.org/I922474255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Kita","raw_affiliation_strings":["Univ. of Tokushima"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Tokushima","institution_ids":["https://openalex.org/I922474255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2795,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81024629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2221","last_page":"2224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.9854000210762024,"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/codebook","display_name":"Codebook","score":0.9056971669197083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7398236989974976},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6735559701919556},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6672192215919495},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6392639875411987},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.6115376353263855},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5644605159759521},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5076652765274048},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46140044927597046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44883793592453003},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15640339255332947},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07684040069580078}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9056971669197083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398236989974976},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6735559701919556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6672192215919495},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6392639875411987},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.6115376353263855},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5644605159759521},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5076652765274048},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46140044927597046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44883793592453003},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15640339255332947},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07684040069580078},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2002-605","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W199108014","https://openalex.org/W382624523","https://openalex.org/W1502984613","https://openalex.org/W2099804331","https://openalex.org/W2117119054","https://openalex.org/W2131711534","https://openalex.org/W2187138504","https://openalex.org/W2266050183"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2736714427","https://openalex.org/W2163679795","https://openalex.org/W2137816434","https://openalex.org/W2017956276","https://openalex.org/W2048606991"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"an":[3],"evaluation":[4],"of":[5,62,75],"European":[6],"Telecommunications":[7],"Standards":[8],"Institute":[9],"(ETSI)":[10],"standard":[11],"Distributed":[12],"Speech":[13],"Recognition":[14],"(DSR)":[15],"front-end":[16,77],"through":[17],"continuous":[18],"word":[19],"recognition":[20,60,73],"on":[21],"a":[22,28],"Japanese":[23],"speech":[24],"corpus":[25],"and":[26,42,66],"proposes":[27],"method,":[29],"the":[30,37,59,68],"Bias":[31],"Removal":[32],"Method":[33],"(BRM),":[34],"that":[35,48,67],"reduces":[36],"distortion":[38],"between":[39],"feature":[40],"vector":[41],"VQ":[43],"codebook.":[44],"Experimental":[45],"results":[46],"show":[47],"using":[49],"nonquantized":[50],"features":[51,65],"in":[52],"acoustic":[53],"model":[54],"training":[55],"procedure":[56],"can":[57,71],"improve":[58,72],"performance":[61],"DSR":[63,76],"fornt-end":[64],"proposed":[69],"method":[70],"performances":[74],"feature.":[78]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}