{"id":"https://openalex.org/W1485785472","doi":"https://doi.org/10.21437/eurospeech.2001-198","title":"Feature extraction from time-frequency matrices for robust speech recognition","display_name":"Feature extraction from time-frequency matrices for robust speech recognition","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W1485785472","doi":"https://doi.org/10.21437/eurospeech.2001-198","mag":"1485785472"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-198","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5000645757","display_name":"Jos\u00e9 C. Segura","orcid":"https://orcid.org/0000-0003-3746-0978"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose C. Segura","raw_affiliation_strings":["[University of Granada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[University of Granada]","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032065113","display_name":"Carmen Ben\u0131\u0301tez","orcid":"https://orcid.org/0000-0002-5407-8335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Carmen Benitez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014325055","display_name":"\u00c1ngel de la Torre","orcid":"https://orcid.org/0000-0002-9736-5190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angel de la Torre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103257592","display_name":"Antonio J. Rubio","orcid":"https://orcid.org/0000-0003-3814-0335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio J. Rubio","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":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1625","last_page":"1628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7422018647193909},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6751635670661926},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6587578058242798},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6190671920776367},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5974865555763245},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5743865966796875},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.557543933391571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5383331179618835},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5258403420448303},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5256724953651428},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5162665843963623},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5059286952018738},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4846096932888031},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4836038649082184},{"id":"https://openalex.org/keywords/discriminant","display_name":"Discriminant","score":0.43647894263267517},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.411682665348053},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1879132091999054},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16432255506515503},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08654099702835083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422018647193909},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6751635670661926},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6587578058242798},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6190671920776367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5974865555763245},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5743865966796875},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.557543933391571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383331179618835},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5258403420448303},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5256724953651428},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5162665843963623},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5059286952018738},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4846096932888031},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4836038649082184},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.43647894263267517},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.411682665348053},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1879132091999054},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16432255506515503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08654099702835083},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2001-198","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.3888","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.3888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sirio.ugr.es/segura/en/../pdfdocs/eusp01b.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W154677192","https://openalex.org/W203795573","https://openalex.org/W206398375","https://openalex.org/W1940991344","https://openalex.org/W2024119716","https://openalex.org/W2108921739","https://openalex.org/W2157821739","https://openalex.org/W2468714721"],"related_works":["https://openalex.org/W2350751952","https://openalex.org/W1999647744","https://openalex.org/W2362114017","https://openalex.org/W3147024994","https://openalex.org/W2063246903","https://openalex.org/W2374055396","https://openalex.org/W1978302214","https://openalex.org/W2021817983","https://openalex.org/W3008559849","https://openalex.org/W2371177901"],"abstract_inverted_index":{"In":[0],"this":[1,93],"paper":[2],"we":[3,28],"present":[4],"a":[5,21,133],"study":[6],"about":[7],"time-frequency":[8,51],"distribution":[9],"of":[10,86,88,99,120],"acoustic-phonetic":[11],"information":[12],"for":[13,37],"the":[14,61,84,97,100],"Spanish":[15,23],"language.":[16],"This":[17,116],"is":[18,107],"based":[19,64],"on":[20,65],"large":[22],"database":[24],"automatically":[25],"labeled,":[26],"and":[27,67,75,91,112,123],"conclude":[29],"that":[30,54,72],"results":[31],"are":[32,55,81,130],"similar":[33],"to":[34,46,95],"those":[35],"obtained":[36],"hand-labeled":[38],"english":[39],"databases.":[40],"We":[41,70],"use":[42,92],"bidimensional":[43],"LDA":[44,89,105],"[1]":[45],"extract":[47],"discriminant":[48],"features":[49],"in":[50,58,110,114,132],"domain":[52,74,79],"(TF)":[53],"more":[56],"robust":[57],"noise":[59],"than":[60],"standard":[62],"ones":[63],"MFCC":[66],"time":[68],"derivatives.":[69],"show":[71],"TF":[73],"its":[76],"corresponding":[77],"transformed":[78],"(CTM)":[80],"equivalent":[82],"from":[83],"point":[85],"view":[87],"analysis":[90],"fact":[94],"reduce":[96],"dimensionality":[98],"problem.":[101],"Finally,":[102],"cascade":[103],"unidimensional":[104],"(CLDA)":[106],"applied":[108],"first":[109],"frequency":[111],"then":[113],"time.":[115],"gives":[117],"better":[118,124],"estimates":[119],"projection":[121],"vectors":[122],"recognition":[125,136],"performance.":[126],"The":[127],"proposed":[128],"techniques":[129],"evaluated":[131],"connected":[134],"digit":[135],"task.":[137],"Utterances":[138],"have":[139],"been":[140],"artificially":[141],"corrupted":[142],"with":[143],"additive":[144],"real":[145],"noises.":[146]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}