{"id":"https://openalex.org/W321571330","doi":"https://doi.org/10.21437/interspeech.2004-333","title":"Continuous speech recognition using joint features derived from the modified group delay function and MFCC","display_name":"Continuous speech recognition using joint features derived from the modified group delay function and MFCC","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W321571330","doi":"https://doi.org/10.21437/interspeech.2004-333","mag":"321571330"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-333","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5085503354","display_name":"Rajesh M. Hegde","orcid":"https://orcid.org/0000-0002-6142-7724"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rajesh Mahanand Hegde","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hema A. Murthy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108508738","display_name":"Venkata Ramana Rao Gadde","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkata Ramana Rao Gadde","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085503354"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9468,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94857193,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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/T10860","display_name":"Speech and Audio Processing","score":0.988099992275238,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9768999814987183,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8713825345039368},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7954519391059875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7528047561645508},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6352036595344543},{"id":"https://openalex.org/keywords/telugu","display_name":"Telugu","score":0.547554075717926},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5022897720336914},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.48696622252464294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47281065583229065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4724942743778229},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4595853388309479},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4403623342514038},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.3830326199531555},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.170986145734787},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.10423547029495239}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8713825345039368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7954519391059875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7528047561645508},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6352036595344543},{"id":"https://openalex.org/C2778756302","wikidata":"https://www.wikidata.org/wiki/Q8097","display_name":"Telugu","level":2,"score":0.547554075717926},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5022897720336914},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.48696622252464294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47281065583229065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4724942743778229},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4595853388309479},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4403623342514038},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3830326199531555},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.170986145734787},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.10423547029495239},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-333","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1491515786","https://openalex.org/W1550888325","https://openalex.org/W2161153290","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2769486197","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2186375278","https://openalex.org/W2749720872","https://openalex.org/W2793748347","https://openalex.org/W4229940372","https://openalex.org/W4250904811","https://openalex.org/W2104528589","https://openalex.org/W2155047054"],"abstract_inverted_index":{"Feature":[0,44],"extraction":[1],"and":[2,55,65,87,159,170,179,197,217,223],"selection":[3],"for":[4,52,78,155,176],"continuous":[5,79,96],"speech":[6,16,80,97,212],"recognition":[7,17,81,107,141,153],"is":[8,110],"a":[9,173],"complex":[10],"task.":[11],"State":[12],"of":[13,39,82,92,94,122,127,194],"the":[14,26,37,48,63,66,95,120,124,156,163,185,195,203,207,211],"art":[15],"systems":[18],"use":[19,62,114,145],"features":[20,77,166],"that":[21,187,193],"are":[22],"derived":[23,46,69,167],"by":[24,104],"ignoring":[25],"Fourier":[27,49,71],"transform":[28,50,72],"phase.":[29],"In":[30,58],"our":[31],"earlier":[32],"studies":[33],"we":[34,61],"have":[35],"shown":[36],"efficacy":[38],"The":[40,140,149,182],"Modified":[41],"Group":[42],"Delay":[43],"(MODGDF)":[45],"from":[47,70],"phase":[51],"phoneme,":[53],"syllable":[54,100],"speaker":[56],"recognition.":[57],"this":[59],"paper":[60],"MODGDF":[64,150,169,188],"popular":[67],"MFCC":[68,171,196,204],"magnitude":[73],"to":[74,133,192,205],"compute":[75],"joint":[76],"two":[83,157],"Indian":[84],"languages":[85,158],"Tamil":[86,178],"Telugu.":[88],"A":[89],"novel":[90],"method":[91],"segmentation":[93],"signal":[98,213],"into":[99],"like":[101],"units":[102,129],"followed":[103],"isolated":[105],"style":[106],"using":[108,168],"HMMs":[109],"used.":[111],"We":[112],"further":[113],"an":[115,135],"innovative":[116],"technique":[117],"which":[118],"transforms":[119],"problem":[121],"detecting":[123],"correct":[125],"string":[126],"syllabic":[128],"with":[130,162,202],"maximum":[131],"likelihood":[132],"finding":[134],"optimal":[136],"state":[137],"sequence":[138],"locally.":[139],"system":[142],"does":[143],"not":[144],"any":[146],"language":[147,224],"models.":[148,225],"gave":[151,172],"promising":[152],"performance":[154],"compared":[160],"well":[161],"MFCC.":[164],"Joint":[165],"10.6%":[174],"improvement":[175,183],"both":[177],"Telugu":[180],"languages.":[181],"reinforces":[184],"hypothesis":[186],"captures":[189],"complementary":[190],"information":[191,209],"can":[198],"be":[199],"used":[200],"along":[201],"capture":[206],"complete":[208],"in":[210,219],"at":[214],"functional":[215],"level":[216],"help":[218],"avoiding":[220],"heavy":[221],"auditory":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}