{"id":"https://openalex.org/W15681473","doi":"https://doi.org/10.21437/icslp.1998-316","title":"Robust features for speech recognition systems","display_name":"Robust features for speech recognition systems","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W15681473","doi":"https://doi.org/10.21437/icslp.1998-316","mag":"15681473"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-316","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5088664270","display_name":"Aruna Bayya","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aruna Bayya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079329589","display_name":"B. Yegnanarayana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B. Yegnanarayana","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088664270"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.00194283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1121","last_page":"0"},"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":0.9994000196456909,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7212453484535217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7203204035758972},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6213492751121521},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6197841763496399},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6082445979118347},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5348438620567322},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5252049565315247},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.50738924741745},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.46189820766448975},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45395487546920776},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.4243113398551941},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41575175523757935},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41297584772109985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3947738707065582},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13958904147148132},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07383161783218384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7212453484535217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7203204035758972},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6213492751121521},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6197841763496399},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6082445979118347},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5348438620567322},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5252049565315247},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.50738924741745},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.46189820766448975},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45395487546920776},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.4243113398551941},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41575175523757935},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41297584772109985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3947738707065582},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13958904147148132},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07383161783218384},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1998-316","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1954606527","https://openalex.org/W1976761624","https://openalex.org/W2090861223","https://openalex.org/W2148154194","https://openalex.org/W2157590573","https://openalex.org/W2179839788"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W4229940372","https://openalex.org/W2186375278","https://openalex.org/W2749720872","https://openalex.org/W2793748347","https://openalex.org/W4250904811","https://openalex.org/W2155047054","https://openalex.org/W2104528589","https://openalex.org/W2379120504"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,96],"propose":[4],"a":[5,113],"set":[6,73],"of":[7,51,69,79,109,121,131],"features":[8,19,33,45],"based":[9,34],"on":[10,35],"group":[11,47,58],"delay":[12,48,59],"spectrum":[13,49,60],"for":[14],"speech":[15],"recognition":[16,86],"systems.":[17],"These":[18],"appear":[20],"to":[21,25,32,42,101,126],"be":[22],"more":[23],"robust":[24],"channel":[26],"variations":[27],"and":[28,83,104,112],"environmental":[29],"changes":[30],"compared":[31],"Melspectral":[36],"coefficients.":[37],"The":[38,57,67],"main":[39],"idea":[40],"is":[41,61,74,124],"derive":[43],"cepstrumlike":[44],"from":[46,54,63],"instead":[50],"deriving":[52],"them":[53],"power":[55],"spectrum.":[56],"computed":[62],"modified":[64],"auto-correlation-like":[65],"function.":[66],"effectiveness":[68],"the":[70,77,93,110,122,129,132],"new":[71,94,133],"feature":[72],"demonstrated":[75],"by":[76],"results":[78,89,99],"both":[80],"speaker-independent":[81],"(SI)":[82],"speaker-dependent":[84],"(SD)":[85],"tasks.":[87],"Preliminary":[88],"indicate":[90],"that":[91],"using":[92],"features,":[95],"can":[97],"obtain":[98],"comparable":[100],"Mel":[102],"cepstra":[103,106],"PLP":[105],"in":[107,116],"most":[108],"cases":[111],"slight":[114],"improvement":[115],"noisy":[117],"cases.":[118],"More":[119],"optimization":[120],"parameters":[123],"needed":[125],"fully":[127],"exploit":[128],"nature":[130],"features.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
