{"id":"https://openalex.org/W23477528","doi":"https://doi.org/10.21437/interspeech.2005-145","title":"Comprehensive modulation representation for automatic speech recognition","display_name":"Comprehensive modulation representation for automatic speech recognition","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W23477528","doi":"https://doi.org/10.21437/interspeech.2005-145","mag":"23477528"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-145","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-145","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":true,"oa_status":"green","oa_url":"https://digitalcommons.uri.edu/ele_facpubs/658","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100392460","display_name":"Yadong Wang","orcid":"https://orcid.org/0000-0003-2067-382X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yadong Wang","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110588131","display_name":"Steven Greenberg","orcid":null},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Steven Greenberg","raw_affiliation_strings":["#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103468122","display_name":"Jayaganesh Swaminathan","orcid":null},"institutions":[{"id":"https://openalex.org/I17626003","display_name":"University of Rhode Island","ror":"https://ror.org/013ckk937","country_code":"US","type":"education","lineage":["https://openalex.org/I17626003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayaganesh Swaminathan","raw_affiliation_strings":["University Of Rhode Island#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Of Rhode Island#TAB#","institution_ids":["https://openalex.org/I17626003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008852017","display_name":"R. Kumaresan","orcid":"https://orcid.org/0000-0002-8897-4568"},"institutions":[{"id":"https://openalex.org/I17626003","display_name":"University of Rhode Island","ror":"https://ror.org/013ckk937","country_code":"US","type":"education","lineage":["https://openalex.org/I17626003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramdas Kumaresan","raw_affiliation_strings":["University Of Rhode Island#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Of Rhode Island#TAB#","institution_ids":["https://openalex.org/I17626003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033417964","display_name":"David Poeppel","orcid":"https://orcid.org/0000-0003-0184-163X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Poeppel","raw_affiliation_strings":["Psychology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Psychology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3619,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78196848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3025","last_page":"3028"},"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":0.9987000226974487,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9923999905586243,"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":0.7701242566108704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7168200612068176},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.6128010749816895},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5883450508117676},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4985959529876709},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48018255829811096},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.4728156328201294},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.45107147097587585},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.4488801658153534},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44662410020828247},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42230409383773804},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.41872847080230713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4132623076438904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4032599925994873},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.15577465295791626},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13443827629089355},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1342158317565918},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06662541627883911}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7701242566108704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168200612068176},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.6128010749816895},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5883450508117676},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4985959529876709},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48018255829811096},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4728156328201294},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45107147097587585},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.4488801658153534},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44662410020828247},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42230409383773804},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.41872847080230713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4132623076438904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4032599925994873},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.15577465295791626},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13443827629089355},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1342158317565918},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06662541627883911},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2005-145","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-145","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"},{"id":"pmh:oai:digitalcommons.uri.edu:ele_facpubs-1657","is_oa":true,"landing_page_url":"https://digitalcommons.uri.edu/ele_facpubs/658","pdf_url":null,"source":{"id":"https://openalex.org/S2764761010","display_name":"Journal of Media Literacy Education","issn_l":"2167-8715","issn":["2167-8715"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310316378","host_organization_name":"National Association for Media Literacy Education","host_organization_lineage":["https://openalex.org/P4310316378"],"host_organization_lineage_names":["National Association for Media Literacy Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical, Computer, and Biomedical Engineering Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.uri.edu:ele_facpubs-1657","is_oa":true,"landing_page_url":"https://digitalcommons.uri.edu/ele_facpubs/658","pdf_url":null,"source":{"id":"https://openalex.org/S2764761010","display_name":"Journal of Media Literacy Education","issn_l":"2167-8715","issn":["2167-8715"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310316378","host_organization_name":"National Association for Media Literacy Education","host_organization_lineage":["https://openalex.org/P4310316378"],"host_organization_lineage_names":["National Association for Media Literacy Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical, Computer, and Biomedical Engineering Faculty Publications","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W143947237","https://openalex.org/W1581322966","https://openalex.org/W2058840389","https://openalex.org/W2080192617","https://openalex.org/W2085085647","https://openalex.org/W2108767768","https://openalex.org/W2111855076","https://openalex.org/W2115737494","https://openalex.org/W2126617887","https://openalex.org/W2129901640","https://openalex.org/W3151807103"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2068642629"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,33,47,103],"new":[3,88],"feature":[4],"representation":[5],"for":[6,67,122,128],"speech":[7,41,69],"recognition":[8,70],"based":[9,31],"on":[10,32,79],"both":[11],"amplitude":[12],"modulation":[13,18,23,34],"spectra":[14,19],"(AMS)":[15],"and":[16,29,119],"frequency":[17],"(FMS).":[20],"A":[21,72],"comprehensive":[22],"spectral":[24],"(CMS)":[25],"approach":[26],"is":[27,43,75],"defined":[28],"analyzed":[30],"model":[35],"of":[36,49,61,94,116],"the":[37,59,62,65,83,87,109,114,117],"band-pass":[38,53],"signal.":[39],"The":[40],"signal":[42],"processed":[44],"first":[45],"by":[46],"bank":[48],"specially":[50],"designed":[51],"auditory":[52],"filters.":[54],"CMS":[55],"are":[56,111],"extracted":[57],"from":[58],"output":[60],"filters":[63],"as":[64],"features":[66,89,101],"automatic":[68],"(ASR).":[71],"significant":[73],"improvement":[74,93],"demonstrated":[76],"in":[77,91],"performance":[78,123],"noisy":[80],"speech.":[81],"On":[82],"Aurora":[84],"2":[85],"task":[86],"result":[90],"an":[92],"23.43%":[95],"relative":[96],"to":[97],"traditional":[98],"mel-cepstrum":[99],"front-end":[100],"using":[102],"3":[104],"GMM":[105],"HMM":[106],"back-end.":[107],"Although":[108],"improvements":[110],"relatively":[112],"modest,":[113],"novelty":[115],"method":[118],"its":[120],"potential":[121],"enhancement":[124],"warrants":[125],"serious":[126],"attention":[127],"future-generation":[129],"ASR":[130],"applications.":[131]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}