{"id":"https://openalex.org/W2766680336","doi":"https://doi.org/10.1007/978-3-319-69900-4_43","title":"Novel Gammatone Filterbank Based Spectro-Temporal Features for Robust Phoneme Recognition","display_name":"Novel Gammatone Filterbank Based Spectro-Temporal Features for Robust Phoneme Recognition","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2766680336","doi":"https://doi.org/10.1007/978-3-319-69900-4_43","mag":"2766680336"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-69900-4_43","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-69900-4_43","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-319-69900-4_43","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067169442","display_name":"Ankit Nagpal","orcid":"https://orcid.org/0000-0003-2927-3320"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ankit Nagpal","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067169442"],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.3285,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55785513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"342","last_page":"350"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.905171275138855},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.8991074562072754},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7573596239089966},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7278082370758057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7075459957122803},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5807417035102844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4483889937400818},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4440808892250061},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4271708130836487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3868005573749542},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.22759872674942017},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1258874535560608}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.905171275138855},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8991074562072754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573596239089966},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7278082370758057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7075459957122803},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5807417035102844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4483889937400818},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4440808892250061},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4271708130836487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3868005573749542},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.22759872674942017},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1258874535560608},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-69900-4_43","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-69900-4_43","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-319-69900-4_43","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-69900-4_43","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1519201259","https://openalex.org/W1990934990","https://openalex.org/W2054139811","https://openalex.org/W2054883573","https://openalex.org/W2077804127","https://openalex.org/W2090861223","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2161025448","https://openalex.org/W2167763959"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2766680336","https://openalex.org/W2133320490","https://openalex.org/W2387604097","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2373675101","https://openalex.org/W3150393935","https://openalex.org/W2125446021"],"abstract_inverted_index":{"Recently,":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"technology":[5],"is":[6,17,81,86],"being":[7],"used":[8,82],"in":[9,51,67,72],"practical":[10],"scenarios":[11],"and":[12,83,95,104,115,143,184,189],"hence,":[13],"robustness":[14],"of":[15,172,181],"ASR":[16],"becoming":[18],"increasingly":[19],"important.":[20],"State-of-the-art":[21],"Mel":[22],"Frequency":[23,106],"Cepstral":[24,107],"Coefficients":[25,108],"(MFCC)":[26],"features":[27,39,46,94,103,110,177],"are":[28,111,124],"known":[29],"to":[30,48,63,119,127,154],"be":[31],"affected":[32],"by":[33,178],"acoustic":[34,161],"noise":[35],"whereas":[36],"physiologically":[37],"motivated":[38],"such":[40],"as":[41],"spectro-temporal":[42,56],"Gabor":[43],"filterbank":[44,62,80,92,99],"(GBFB)":[45],"intend":[47],"perform":[49],"better":[50,169],"signal":[52],"degradation":[53],"conditions.":[54],"The":[55],"GBFB":[57,89,96],"feature":[58,165],"extraction":[59],"incorporates":[60],"mel":[61,91],"mimic":[64],"frequency":[65,145,191],"mapping":[66],"the":[68,73],"Basilar":[69],"Membrane":[70],"(BM)":[71],"inner":[74],"ear.":[75],"In":[76],"this":[77],"paper,":[78],"Gammatone":[79,98,105],"a":[84],"comparison":[85],"done":[87],"between":[88],"with":[90,97,113,139,160],"(GBFBmel)":[93],"(GBFBGamm)":[100],"features.":[101],"MFCC":[102],"(GFCC)":[109],"concatenated":[112],"GBFBmel":[114],"GBFBGamm":[116],"features,":[117],"respectively,":[118],"improve":[120],"recognition":[121,130],"performance.":[122],"Experiments":[123],"carried":[125],"out":[126],"calculate":[128],"phoneme":[129],"accuracy":[131],"(PRA),":[132],"on":[133],"TIMIT":[134],"database":[135],"(without":[136],"\u2018sa\u2019":[137],"sentences),":[138],"additive":[140],"white,":[141,187],"volvo":[142,188],"high":[144,190],"noises":[146],"at":[147],"various":[148],"SNR":[149],"levels":[150],"from":[151],"\u22125":[152],"dB":[153],"20":[155],"dB.":[156],"Results":[157],"show":[158],"that,":[159],"modeling":[162],"only,":[163],"proposed":[164],"set":[166],"(GBFBGamm+GFCC)":[167],"performs":[168],"(in":[170],"terms":[171],"PRA":[173],"%),":[174],"than":[175],"GBFBmel+MFCC":[176],"an":[179],"average":[180],"1%,":[182],"0.2%":[183],"0.8%":[185],"for":[186],"noises,":[192],"respectively.":[193]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}