{"id":"https://openalex.org/W82863161","doi":"https://doi.org/10.21437/interspeech.2005-148","title":"Auditory image model features for automatic speech recognition","display_name":"Auditory image model features for automatic speech recognition","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W82863161","doi":"https://doi.org/10.21437/interspeech.2005-148","mag":"82863161"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-148","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010815107","display_name":"Mario E. Munich","orcid":"https://orcid.org/0000-0002-6665-7473"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mario E. Munich","raw_affiliation_strings":["California  Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California  Institute of Technology","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103431069","display_name":"Qiguang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiguang Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.00514668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3037","last_page":"3040"},"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":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700461149215698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7270802855491638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4895061254501343},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46540337800979614},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3289549946784973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700461149215698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7270802855491638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4895061254501343},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46540337800979614},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3289549946784973}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2005-148","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/W1663847965","https://openalex.org/W1874653086","https://openalex.org/W2003513536","https://openalex.org/W2045956438","https://openalex.org/W2060539877","https://openalex.org/W2129382696","https://openalex.org/W2132606418","https://openalex.org/W2162362731"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2058170566"],"abstract_inverted_index":{"Conventional":[0],"speech":[1,25],"recognition":[2,48,72],"engines":[3],"extract":[4],"Mel":[5],"Frequency":[6],"Cepstral":[7],"Coefficients":[8],"(MFCC)":[9],"features":[10],"from":[11],"incoming":[12],"speech.":[13],"This":[14],"paper":[15],"presents":[16],"a":[17,34,68],"novel":[18],"approach":[19,66],"for":[20],"feature":[21],"extraction":[22],"in":[23,71],"which":[24],"is":[26],"processed":[27],"according":[28],"to":[29],"the":[30,42,52,61,64],"Auditory":[31],"Image":[32],"Model,":[33],"model":[35],"of":[36],"human":[37],"psychoacoustics.":[38],"We":[39],"fist":[40],"describe":[41],"proposed":[43],"frontend,":[44],"then":[45],"we":[46],"present":[47],"results":[49,59],"obtained":[50],"with":[51,56],"TIMIT":[53],"database.":[54],"Comparing":[55],"previously":[57],"published":[58],"on":[60],"same":[62],"task,":[63],"new":[65],"achieves":[67],"10%":[69],"improvement":[70],"accuracy.":[73]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}