{"id":"https://openalex.org/W4299576595","doi":"https://doi.org/10.21437/icslp.2000-77","title":"Perceptual harmonic cepstral coefficients as the front-end for speech recognition","display_name":"Perceptual harmonic cepstral coefficients as the front-end for speech recognition","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W4299576595","doi":"https://doi.org/10.21437/icslp.2000-77"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-77","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-77","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","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/A5100729048","display_name":"Liang Gu","orcid":"https://orcid.org/0000-0001-9035-5494"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liang Gu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026459097","display_name":"Kenneth Rose","orcid":"https://orcid.org/0000-0001-9463-2647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenneth Rose","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100729048"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6519,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.7543538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"vol. 1, 309","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9056000113487244,"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":0.9056000113487244,"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":0.7418769598007202},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.67577064037323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5291735529899597},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5222959518432617},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5214192867279053},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.480035662651062},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.475195050239563},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3596757650375366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2975502610206604},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.21626505255699158},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1775836944580078},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17514535784721375}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7418769598007202},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.67577064037323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5291735529899597},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5222959518432617},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5214192867279053},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.480035662651062},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.475195050239563},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3596757650375366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2975502610206604},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.21626505255699158},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1775836944580078},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17514535784721375},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2000-77","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-77","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.1095","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.1095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.scl.ece.ucsb.edu/html/../pubs/pubs_B/b00_4.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2736574136","https://openalex.org/W2373675101","https://openalex.org/W2038216521","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W894828327","https://openalex.org/W2136559180"],"abstract_inverted_index":{"Perceptual":[0],"harmonic":[1],"cepstral":[2,93],"coefficients":[3],"(PHCC)":[4],"are":[5,24],"proposed":[6],"as":[7],"features":[8],"to":[9,38,57,91,104],"extract":[10],"for":[11,131],"speech":[12,23,68],"recognition.":[13],"Pitch":[14],"estimation":[15],"and":[16,21,51,61,80,126,136],"classification":[17,50],"into":[18],"voiced,":[19],"unvoiced,":[20],"transitional":[22],"performed":[25],"by":[26],"a":[27],"spectro-temporal":[28],"auto-correlation":[29],"technique.":[30],"A":[31,43],"peak":[32],"picking":[33],"algorithm":[34],"is":[35,55,87,102],"then":[36],"employed":[37],"precisely":[39],"locate":[40],"pitch":[41,53],"harmonics.":[42],"weighting":[44],"function,":[45],"which":[46],"depends":[47],"on":[48],"the":[49,52,58,66,81,84,111,132],"harmonics,":[54],"applied":[56,103],"power":[59,74],"spectrum":[60,75],"ensures":[62],"accurate":[63],"representation":[64],"of":[65,83,110,120],"voiced":[67],"spectral":[69],"envelope.":[70],"The":[71],"harmonics":[72],"weighted":[73],"undergoes":[76],"mel-scaled":[77],"band-pass":[78],"filtering,":[79],"logenergy":[82],"filters'":[85],"output":[86],"discrete":[88],"cosine":[89],"transformed":[90],"produce":[92],"coefficients.":[94],"For":[95],"perceptual":[96],"considerations,":[97],"within-filter":[98],"cubic-root":[99],"amplitude":[100,106],"compression":[101],"reduce":[105],"variation":[107],"without":[108],"compromise":[109],"gain":[112],"invariance":[113],"properties.":[114],"Experiments":[115],"show":[116],"substantial":[117],"recognition":[118],"gains":[119],"PHCC":[121],"over":[122],"MFCC,":[123],"with":[124],"48%":[125],"15%":[127],"error":[128],"rate":[129],"reduction":[130],"Mandarin":[133],"digit":[134],"database":[135],"E-set,":[137],"respectively.":[138]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}