{"id":"https://openalex.org/W14539640","doi":"https://doi.org/10.21437/interspeech.2010-660","title":"A feature extraction method for automatic speech recognition based on the cochlear nucleus","display_name":"A feature extraction method for automatic speech recognition based on the cochlear nucleus","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W14539640","doi":"https://doi.org/10.21437/interspeech.2010-660","mag":"14539640"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5027551410","display_name":"Serajul Haque","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Serajul Haque","raw_affiliation_strings":["School of Electrical, Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017213156","display_name":"Roberto Togneri","orcid":"https://orcid.org/0000-0002-3778-4633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Togneri","raw_affiliation_strings":["School of Electrical, Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027551410"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3383,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.51797054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2454","last_page":"2457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9954000115394592,"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/companding","display_name":"Companding","score":0.776802659034729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7724411487579346},{"id":"https://openalex.org/keywords/cochlear-nucleus","display_name":"Cochlear nucleus","score":0.678370475769043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6686846613883972},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6607301235198975},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.576387345790863},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5567688345909119},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5119253396987915},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46163129806518555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44052428007125854},{"id":"https://openalex.org/keywords/auditory-system","display_name":"Auditory system","score":0.42529425024986267},{"id":"https://openalex.org/keywords/nucleus","display_name":"Nucleus","score":0.2718372344970703},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06945809721946716},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.06631296873092651}],"concepts":[{"id":"https://openalex.org/C104250799","wikidata":"https://www.wikidata.org/wiki/Q1780765","display_name":"Companding","level":4,"score":0.776802659034729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7724411487579346},{"id":"https://openalex.org/C2777662796","wikidata":"https://www.wikidata.org/wiki/Q387776","display_name":"Cochlear nucleus","level":3,"score":0.678370475769043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686846613883972},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6607301235198975},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.576387345790863},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5567688345909119},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5119253396987915},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46163129806518555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44052428007125854},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.42529425024986267},{"id":"https://openalex.org/C2780723820","wikidata":"https://www.wikidata.org/wiki/Q1934178","display_name":"Nucleus","level":2,"score":0.2718372344970703},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06945809721946716},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.06631296873092651},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C40409654","wikidata":"https://www.wikidata.org/wiki/Q375889","display_name":"Orthogonal frequency-division multiplexing","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/08e7ffee-4886-4c68-8469-7d967b1bfb00","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/08e7ffee-4886-4c68-8469-7d967b1bfb00","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Haque, S & Togneri, R 2010, A Feature Extraction Method for Automatic Speech Recognition Based on the Cochlear Nucleus. in K Hirose (ed.), Proceedings of the 11th Annual Conference of the International Speech Communication Association (Interspeech 2010). Makuhari, Chiba, Japan edn, vol. CD Rom, ISCA, Makuhari, Chiba, Japan, pp. 2454-2457, 11th Annual Conference of the International Speech Communication Association, Makuhari, Japan, 26/09/10.","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6700000166893005,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W15113896","https://openalex.org/W1822181003","https://openalex.org/W1919639142","https://openalex.org/W2014098799","https://openalex.org/W2116624898","https://openalex.org/W2143658670","https://openalex.org/W2153447968","https://openalex.org/W2158483598","https://openalex.org/W2400113920","https://openalex.org/W2990482378"],"related_works":["https://openalex.org/W2084899843","https://openalex.org/W1971893190","https://openalex.org/W101695054","https://openalex.org/W2415745046","https://openalex.org/W2515425874","https://openalex.org/W2116176074","https://openalex.org/W1488206613","https://openalex.org/W2010393728","https://openalex.org/W1992890284","https://openalex.org/W2080137904"],"abstract_inverted_index":{"Motivated":[0],"by":[1],"the":[2,17,22,26,29,50,56,61,66,99,104,124],"human":[3],"auditory":[4,43,126,133],"system,":[5],"a":[6,37,75],"feature":[7],"extraction":[8],"method":[9,35,78],"for":[10,81],"automatic":[11],"speech":[12],"recognition":[13,108,114],"(ASR)":[14],"based":[15],"on":[16],"differential":[18],"processing":[19,63,95,101],"strategy":[20],"of":[21,28,72],"AVCN,":[23],"PVCN":[24],"and":[25,118],"DCN":[27],"cochlear":[30,105,135],"nucleus":[31],"is":[32,79],"proposed.":[33],"The":[34],"utilizes":[36,55],"zero-crossing":[38],"with":[39],"peak":[40],"amplitudes":[41],"(ZCPA)":[42],"model":[44],"as":[45,96],"synchrony":[46,91],"detector":[47],"to":[48,64,89],"discriminate":[49],"low":[51],"frequency":[52],"formants.":[53],"It":[54],"mean":[57],"rate":[58],"information":[59],"in":[60,98,103,116,119],"synapse":[62],"capture":[65],"very":[67],"rapidly":[68],"changing":[69],"dynamic":[70],"nature":[71],"speech.":[73],"Additionally,":[74],"temporal":[76],"companding":[77],"utilized":[80],"spectral":[82],"enhancement":[83],"through":[84],"two-tone":[85],"suppression.":[86],"We":[87],"propose":[88],"separate":[90],"detection":[92],"from":[93],"synaptic":[94],"observed":[97],"parallel":[100],"methodology":[102],"nucleus.":[106],"HMM":[107],"using":[109],"isolated":[110],"digits":[111],"showed":[112],"improved":[113],"rates":[115],"clean":[117],"nonstationary":[120],"noise":[121],"conditions":[122],"than":[123],"existing":[125],"model.":[127,139],"Index":[128],"Terms:":[129],"Speech":[130],"recognition,":[131],"zero-crossings,":[132],"model,":[134],"nucleus,":[136],"hidden":[137],"Markov":[138]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}