{"id":"https://openalex.org/W89056307","doi":"https://doi.org/10.21437/eurospeech.2001-615","title":"Is speech data clustered? - statistical analysis of cepstral features","display_name":"Is speech data clustered? - statistical analysis of cepstral features","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W89056307","doi":"https://doi.org/10.21437/eurospeech.2001-615","mag":"89056307"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-615","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-615","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":"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/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018962547","display_name":"Ismo K\u00e4rkk\u00e4inen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ismo K\u00e4rkk\u00e4inen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037846871","display_name":"Pasi Fr\u00e4nti","orcid":"https://orcid.org/0000-0002-9554-2827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pasi Fr\u00e4nti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3638,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.64713234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2627","last_page":"2630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.744178056716919},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.7412030696868896},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.7228788733482361},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6560807228088379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.632537305355072},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6281305551528931},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6256746649742126},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6187853813171387},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.594086766242981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5551846623420715},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5026161670684814},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4527299106121063},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42453524470329285},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.41879719495773315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744178056716919},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.7412030696868896},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7228788733482361},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6560807228088379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.632537305355072},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6281305551528931},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6256746649742126},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6187853813171387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.594086766242981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5551846623420715},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5026161670684814},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4527299106121063},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42453524470329285},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.41879719495773315},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2001-615","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-615","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:10.1.1.58.3968","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.3968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/tkinnu/research/pdf/IsSpeechClustered.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W50589544","https://openalex.org/W2050693797","https://openalex.org/W2126782412","https://openalex.org/W2134383396","https://openalex.org/W3019584399"],"related_works":["https://openalex.org/W4246349004","https://openalex.org/W2181871477","https://openalex.org/W2061163896","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2432604435","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W2089229568"],"abstract_inverted_index":{"Speech":[0],"analysis":[1,9],"applications":[2],"are":[3,25],"typically":[4],"based":[5],"on":[6],"short-term":[7],"spectral":[8],"of":[10,79,90],"the":[11,41,48,55,69,77,80,91],"speech":[12,84],"signal.":[13],"Feature":[14],"extraction":[15],"process":[16],"outputs":[17],"one":[18],"feature":[19,49,56,70],"vector":[20,37],"per":[21],"frame.":[22],"The":[23],"features":[24],"further":[26],"processed":[27],"by":[28],"application-dependent":[29],"techniques,":[30],"such":[31],"as":[32],"hidden":[33],"Markov":[34],"models":[35],"or":[36],"quantization.":[38],"Independent":[39],"from":[40],"application,":[42],"it":[43],"is":[44,65,76],"often":[45],"desirable":[46],"that":[47],"vectors":[50],"form":[51],"separable":[52],"clusters":[53,81],"in":[54,68,82],"space.":[57],"In":[58],"this":[59],"work,":[60],"we":[61],"study":[62],"whether":[63],"data":[64],"really":[66],"clustered":[67],"space":[71],"and,":[72],"if":[73],"so,":[74],"what":[75],"number":[78],"typical":[83],"data.":[85],"We":[86],"consider":[87],"different":[88],"forms":[89],"widely":[92],"used":[93],"cepstral":[94],"features.":[95]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}