{"id":"https://openalex.org/W2161025448","doi":"https://doi.org/10.1109/icassp.2009.4960661","title":"An auditory-based feature for robust speech recognition","display_name":"An auditory-based feature for robust speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2161025448","doi":"https://doi.org/10.1109/icassp.2009.4960661","mag":"2161025448"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960661","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/A5079984408","display_name":"Yang Shao","orcid":"https://orcid.org/0000-0002-4870-7406"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Shao","raw_affiliation_strings":["Computer Science and Engineering Department, Ohio State Uinversity, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025797022","display_name":"Zhaozhang Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaozhang Jin","raw_affiliation_strings":["Computer Science and Engineering Department, Ohio State Uinversity, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Computer Science and Engineering Department, Ohio State Uinversity, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102163048","display_name":"Soundararajan Srinivasan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soundararajan Srinivasan","raw_affiliation_strings":["Research and Technology Center, Robert Bosch Limited Liability Company, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Research and Technology Center, Robert Bosch Limited Liability Company, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210120115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079984408"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.2816,"has_fulltext":false,"cited_by_count":128,"citation_normalized_percentile":{"value":0.94555342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4625","last_page":"4628"},"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":0.9991999864578247,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8302434682846069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106306195259094},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8064141273498535},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6450958847999573},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5955564379692078},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5185809135437012},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5117821097373962},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.49329227209091187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48938411474227905},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4855053424835205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4652358591556549},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.24685660004615784},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09644228219985962}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8302434682846069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106306195259094},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8064141273498535},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6450958847999573},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5955564379692078},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5185809135437012},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5117821097373962},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.49329227209091187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48938411474227905},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4855053424835205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4652358591556549},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.24685660004615784},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09644228219985962},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960661","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.1803","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.1803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/SJWS.icassp09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5099999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W1575829986","https://openalex.org/W1766888123","https://openalex.org/W1973746598","https://openalex.org/W1974387177","https://openalex.org/W1991112797","https://openalex.org/W2013020033","https://openalex.org/W2013312573","https://openalex.org/W2045036776","https://openalex.org/W2072184010","https://openalex.org/W2074354966","https://openalex.org/W2075036909","https://openalex.org/W2090861223","https://openalex.org/W2102346872","https://openalex.org/W2126622418","https://openalex.org/W2131470542","https://openalex.org/W2137075158","https://openalex.org/W2143855671","https://openalex.org/W2145475542","https://openalex.org/W2146608839","https://openalex.org/W2149425615","https://openalex.org/W2478884216","https://openalex.org/W2561557072","https://openalex.org/W4256399001","https://openalex.org/W6675700563"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W2766680336","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W4289830142","https://openalex.org/W2125446021","https://openalex.org/W2133320490","https://openalex.org/W2373675101","https://openalex.org/W3150393935"],"abstract_inverted_index":{"A":[0],"conventional":[1,69],"automatic":[2],"speech":[3,23,40],"recognizer":[4],"does":[5],"not":[6],"perform":[7],"well":[8],"in":[9,24],"the":[10,62,77],"presence":[11],"of":[12],"noise,":[13],"while":[14],"human":[15],"listeners":[16],"are":[17,47],"able":[18],"to":[19],"segregate":[20],"and":[21],"recognize":[22],"noisy":[25],"conditions.":[26],"We":[27,72],"study":[28],"a":[29,51,81],"novel":[30],"feature":[31,64,79],"based":[32],"on":[33,54],"an":[34],"auditory":[35,83],"periphery":[36],"model":[37],"for":[38],"robust":[39],"recognition.":[41],"Specifically,":[42],"gammatone":[43,55],"frequency":[44],"cepstral":[45,52],"coefficients":[46],"derived":[48],"by":[49],"applying":[50],"analysis":[53,85],"filterbank":[56],"responses.":[57],"Our":[58],"evaluations":[59],"show":[60],"that":[61,75],"proposed":[63,78],"performs":[65],"considerably":[66],"better":[67],"than":[68],"acoustic":[70],"features.":[71],"further":[73],"demonstrate":[74],"integrating":[76],"with":[80],"computational":[82],"scene":[84],"system":[86],"yields":[87],"promising":[88],"recognition":[89],"performance.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}