{"id":"https://openalex.org/W2167033870","doi":"https://doi.org/10.1109/iscslp.2010.5684893","title":"DCT-based processing of dynamic features for robust speech recognition","display_name":"DCT-based processing of dynamic features for robust speech recognition","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2167033870","doi":"https://doi.org/10.1109/iscslp.2010.5684893","mag":"2167033870"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","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/A5102164271","display_name":"Wen\u2010Chi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Chi Lin","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000054510","display_name":"Hao-teng Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hao-Teng Fan","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-Weih Hung","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193365169"],"apc_list":null,"apc_paid":null,"fwci":0.3201,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54882155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.9199264645576477},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8957184553146362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7568120956420898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7067787647247314},{"id":"https://openalex.org/keywords/modified-discrete-cosine-transform","display_name":"Modified discrete cosine transform","score":0.5994887948036194},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5715195536613464},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5694327354431152},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4747500717639923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4710060656070709},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.44907456636428833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.448818564414978},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4387008845806122},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39019328355789185},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.35084742307662964},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2062670886516571},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15053528547286987},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1450585424900055}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.9199264645576477},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8957184553146362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7568120956420898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7067787647247314},{"id":"https://openalex.org/C28726691","wikidata":"https://www.wikidata.org/wiki/Q1268231","display_name":"Modified discrete cosine transform","level":5,"score":0.5994887948036194},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5715195536613464},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5694327354431152},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4747500717639923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4710060656070709},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.44907456636428833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.448818564414978},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4387008845806122},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39019328355789185},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.35084742307662964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2062670886516571},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15053528547286987},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1450585424900055},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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:10.1109/iscslp.2010.5684893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1535749512","https://openalex.org/W1971332722","https://openalex.org/W2031614119","https://openalex.org/W2096051479","https://openalex.org/W2097444044","https://openalex.org/W2137075158","https://openalex.org/W2397292509","https://openalex.org/W6632381328","https://openalex.org/W6712041054"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W2766680336","https://openalex.org/W1980297060","https://openalex.org/W2133320490","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2373675101","https://openalex.org/W2548564146"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"explore":[4],"the":[5,23,33,42,47,65,78,83,88],"various":[6],"properties":[7],"of":[8,36],"cepstral":[9,38],"time":[10],"coefficients":[11,39],"(CTC)":[12],"in":[13,86],"speech":[14,69],"recognition,":[15],"and":[16,41,63],"then":[17],"propose":[18],"several":[19],"methods":[20,80],"to":[21],"refine":[22],"CTC":[24,31,85],"construction":[25],"process.":[26],"It":[27],"is":[28,96],"found":[29],"that":[30,77],"are":[32,45],"filtered":[34],"version":[35],"mel-frequency":[37],"(MFCC),":[40],"used":[43],"filters":[44,57],"from":[46],"discrete":[48],"cosine":[49],"transform":[50],"(DCT)":[51],"matrix.":[52],"We":[53],"modify":[54],"these":[55],"DCT-based":[56],"by":[58],"windowing,":[59],"removing":[60],"DC":[61],"gain,":[62],"varying":[64],"filter":[66],"length.":[67],"The":[68,91],"recognition":[70,89],"task":[71],"using":[72],"Aurora-2":[73],"digit":[74],"database":[75],"show":[76],"proposed":[79],"can":[81],"enhance":[82],"original":[84],"improving":[87],"accuracy.":[90],"resulting":[92],"relative":[93],"error":[94],"reduction":[95],"around":[97],"20%.":[98]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}