{"id":"https://openalex.org/W2069723558","doi":"https://doi.org/10.21437/icslp.2000-475","title":"A high-performance auditory feature for robust speech recognition","display_name":"A high-performance auditory feature for robust speech recognition","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W2069723558","doi":"https://doi.org/10.21437/icslp.2000-475","mag":"2069723558"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-475","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","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/A5100350165","display_name":"Qi Li","orcid":"https://orcid.org/0000-0001-8776-8730"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qi Li","raw_affiliation_strings":["BELL LABORATORIES"],"affiliations":[{"raw_affiliation_string":"BELL LABORATORIES","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100350165"],"corresponding_institution_ids":["https://openalex.org/I72090969"],"apc_list":null,"apc_paid":null,"fwci":1.5906,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.8394944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"vol. 3, 51","last_page":"54"},"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/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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":0.7548844218254089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262091040611267},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4851561188697815},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.415314257144928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3456346392631531},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33975231647491455}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7548844218254089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262091040611267},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4851561188697815},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.415314257144928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3456346392631531},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33975231647491455},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2000-475","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","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":7,"referenced_works":["https://openalex.org/W151018310","https://openalex.org/W1992468098","https://openalex.org/W2013020033","https://openalex.org/W2090861223","https://openalex.org/W2117647530","https://openalex.org/W2137075158","https://openalex.org/W2148154194"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W2601157893","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2112208972","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W2151520854","https://openalex.org/W2811390910"],"abstract_inverted_index":{"An":[0],"auditory":[1,21,42],"feature":[2,24,77],"extraction":[3,25],"algorithm":[4,26],"for":[5],"robust":[6],"speech":[7],"recognition":[8,50,58],"in":[9,59,87,93],"adverse":[10],"acoustic":[11,91],"environments":[12,92],"is":[13],"proposed.":[14],"Based":[15],"on":[16,55,85],"the":[17,23,75,94],"analysis":[18],"of":[19,28],"human":[20],"system,":[22],"consists":[27],"several":[29],"modules:":[30],"FFT,":[31],"outer-middle-ear":[32],"transfer":[33],"function,":[34],"frequency":[35],"conversion":[36],"from":[37],"linear":[38],"to":[39,70,81],"Bark":[40],"scales,":[41],"filtering,":[43],"nonlinearity,":[44],"and":[45,61,66,72,89],"discrete":[46],"cosine":[47],"transform.":[48],"Three":[49],"experiments":[51],"have":[52],"been":[53],"conducted":[54],"connected":[56],"digit":[57],"wireless":[60],"land-line":[62],"communications":[63],"using":[64],"handsets":[65],"handsfree":[67],"microphones.":[68],"Compared":[69],"LPCC":[71],"MFCC":[73],"features,":[74],"proposed":[76],"has":[78],"shown":[79],"11%":[80],"23%":[82],"error-rate":[83],"reductions":[84],"average":[86],"handset":[88],"hands-free":[90],"experiments.":[95]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}