{"id":"https://openalex.org/W2133123671","doi":"https://doi.org/10.1109/asru.2009.5373305","title":"Short-time instantaneous frequency and bandwidth features for speech recognition","display_name":"Short-time instantaneous frequency and bandwidth features for speech recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2133123671","doi":"https://doi.org/10.1109/asru.2009.5373305","mag":"2133123671"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition &amp; Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doi.org/10.1109/ASRU.2009.5373305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","School of Electrical and Computer Engg., National Technical University of Athens, Greece"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"School of Electrical and Computer Engg., National Technical University of Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084949286","display_name":"Alexandros Potamianos","orcid":"https://orcid.org/0009-0007-1532-5288"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alexandros Potamianos","raw_affiliation_strings":["Department of Electronics and Computer Engineering, Technical University of Crete, Chania, Greece","Department of Electronics & Computer Engineering, Technical University of Crete, Chania, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Computer Engineering, Technical University of Crete, Chania, Greece","institution_ids":["https://openalex.org/I55741626"]},{"raw_affiliation_string":"Department of Electronics & Computer Engineering, Technical University of Crete, Chania, Greece","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115044944","display_name":"Dimitrios Dimitriadis","orcid":"https://orcid.org/0000-0001-8483-0105"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Dimitriadis","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","School of Electrical and Computer Engg., National Technical University of Athens, Greece"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"School of Electrical and Computer Engg., National Technical University of Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027494724"],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":null,"apc_paid":null,"fwci":1.0736,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77415274,"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":"103","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/filter-bank","display_name":"Filter bank","score":0.8035483360290527},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7434287667274475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7178202271461487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6731782555580139},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5469328761100769},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5274037718772888},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4966581463813782},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48387444019317627},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4375470280647278},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.42047226428985596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41551780700683594},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3776162266731262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36637741327285767},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1297723650932312},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1272105574607849}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8035483360290527},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7434287667274475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178202271461487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6731782555580139},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5469328761100769},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5274037718772888},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4966581463813782},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48387444019317627},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4375470280647278},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.42047226428985596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41551780700683594},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3776162266731262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36637741327285767},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1297723650932312},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1272105574607849},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2009.5373305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition &amp; Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/32691","is_oa":true,"landing_page_url":"http://doi.org/10.1109/ASRU.2009.5373305","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2009","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/32691","is_oa":true,"landing_page_url":"http://doi.org/10.1109/ASRU.2009.5373305","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2009","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2004495669","https://openalex.org/W2014893602","https://openalex.org/W2103755349","https://openalex.org/W2108767768","https://openalex.org/W2109225367","https://openalex.org/W2114537326","https://openalex.org/W2118209063","https://openalex.org/W2118864322","https://openalex.org/W2141815139","https://openalex.org/W2157000920","https://openalex.org/W2163212981","https://openalex.org/W2163669870"],"related_works":["https://openalex.org/W2766680336","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2133320490","https://openalex.org/W2125446021","https://openalex.org/W3150393935","https://openalex.org/W2980055100","https://openalex.org/W2186790562","https://openalex.org/W2548564146","https://openalex.org/W2756038079"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4,65],"the":[5,22,26,66,78,86,99,103,115,155],"performance":[6,68],"of":[7,25,37,69,107,122],"modulation":[8],"related":[9,128],"features":[10,42,80,117,129],"and":[11,31,49,58,109,118,140],"normalized":[12],"spectral":[13],"moments":[14],"for":[15,56,114,137,144,154],"automatic":[16],"speech":[17,57],"recognition.":[18,60],"We":[19],"focus":[20],"on":[21],"short-time":[23],"averages":[24],"amplitude":[27],"weighted":[28],"instantaneous":[29],"frequencies":[30],"bandwidths,":[32],"computed":[33],"at":[34,131],"each":[35],"subband":[36],"a":[38,96],"mel-spaced":[39],"filterbank.":[40],"Similar":[41],"have":[43,50],"been":[44,51],"proposed":[45,79,116],"in":[46,85],"previous":[47],"studies,":[48],"successfully":[52],"combined":[53],"with":[54,120],"MFCCs":[55,136],"speaker":[59],"Our":[61],"goal":[62],"is":[63,74],"to":[64,98,148],"stand-alone":[67],"these":[70],"features.":[71],"First,":[72],"it":[73],"experimentally":[75],"shown":[76],"that":[77,126],"are":[81,112],"only":[82],"moderately":[83],"correlated":[84],"frequency":[87,127],"domain,":[88],"and,":[89],"unlike":[90],"MFCCs,":[91],"they":[92],"do":[93],"not":[94],"require":[95],"transformation":[97],"cepstral":[100],"domain.":[101],"Next,":[102],"filterbank":[104],"parameters":[105],"(number":[106],"filters":[108],"filter":[110],"overlap)":[111],"investigated":[113],"compared":[119],"those":[121],"MFCCs.":[123],"Results":[124],"show":[125],"perform":[130],"least":[132],"as":[133,135],"well":[134],"clean":[138],"conditions,":[139],"yield":[141],"superior":[142],"results":[143],"noisy":[145],"conditions;":[146],"up":[147],"50%":[149],"relative":[150],"error":[151],"rate":[152],"reduction":[153],"AURORA3":[156],"Spanish":[157],"task.":[158]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
