{"id":"https://openalex.org/W2183815461","doi":"https://doi.org/10.1109/sped.2015.7343105","title":"Phonetic segmentation of speech using STEP and t-SNE","display_name":"Phonetic segmentation of speech using STEP and t-SNE","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2183815461","doi":"https://doi.org/10.1109/sped.2015.7343105","mag":"2183815461"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2015.7343105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2015.7343105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038722127","display_name":"Mircea Giurgiu","orcid":"https://orcid.org/0009-0007-9789-6083"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mircea Giurgiu","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"82","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9988999962806702,"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/margin","display_name":"Margin (machine learning)","score":0.8147662878036499},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7926527261734009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7904660105705261},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.6819340586662292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6745434999465942},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.611161470413208},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.589470386505127},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5689619779586792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5645322799682617},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4783701002597809},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4616282284259796},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4594385027885437},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42858463525772095},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4148210883140564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09142547845840454}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.8147662878036499},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7926527261734009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904660105705261},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.6819340586662292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6745434999465942},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.611161470413208},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.589470386505127},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5689619779586792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5645322799682617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4783701002597809},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4616282284259796},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4594385027885437},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42858463525772095},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4148210883140564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09142547845840454},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2015.7343105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2015.7343105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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":31,"referenced_works":["https://openalex.org/W1545406001","https://openalex.org/W1588479472","https://openalex.org/W1608367484","https://openalex.org/W1680797894","https://openalex.org/W1788348338","https://openalex.org/W1986410788","https://openalex.org/W2049686551","https://openalex.org/W2054665642","https://openalex.org/W2059167550","https://openalex.org/W2075076415","https://openalex.org/W2149489931","https://openalex.org/W2157444450","https://openalex.org/W2169711598","https://openalex.org/W2171631590","https://openalex.org/W2171752983","https://openalex.org/W2187089797","https://openalex.org/W2396325258","https://openalex.org/W2396623051","https://openalex.org/W2401167848","https://openalex.org/W2403055070","https://openalex.org/W2407733515","https://openalex.org/W2408737549","https://openalex.org/W3127686677","https://openalex.org/W4247750718","https://openalex.org/W6632590417","https://openalex.org/W6683161245","https://openalex.org/W6712116294","https://openalex.org/W6713448933","https://openalex.org/W6713527878","https://openalex.org/W6713742277","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2542746790","https://openalex.org/W1558302546","https://openalex.org/W4214818988","https://openalex.org/W2168417340","https://openalex.org/W4255793089","https://openalex.org/W2402157757","https://openalex.org/W2738297198","https://openalex.org/W1886519670","https://openalex.org/W2121987127","https://openalex.org/W2064292782"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,14,26,118,125],"first":[4],"attempt":[5],"to":[6,71,85,97],"perform":[7],"phoneme-level":[8],"segmentation":[9,110],"of":[10,48,78,112],"speech":[11],"based":[12],"on":[13],"perceptual":[15],"representation":[16],"-":[17,24,30],"the":[18,31,41,46,79,130],"Spectro":[19],"Temporal":[20],"Excitation":[21],"Pattern":[22],"(STEP)":[23],"and":[25,67,75,91,122],"dimensionality":[27],"reduction":[28],"technique":[29],"t-Distributed":[32],"Stochastic":[33],"Neighbour":[34],"Embedding":[35],"(t-SNE).":[36],"The":[37,81],"method":[38,82],"searches":[39],"for":[40,57],"true":[42],"phonetic":[43,65],"boundaries":[44],"in":[45,88],"vicinity":[47],"those":[49],"produced":[50],"by":[51,115],"an":[52],"HMM-based":[53],"segmentation.":[54],"It":[55],"looks":[56],"perceptually-salient":[58],"spectral":[59],"changes":[60],"which":[61],"occur":[62],"at":[63,124],"these":[64],"transitions,":[66],"exploits":[68],"t-SNE's":[69],"ability":[70],"capture":[72],"both":[73],"local":[74],"global":[76],"structure":[77],"data.":[80],"is":[83,93],"intended":[84],"be":[86],"used":[87],"any":[89,98],"language":[90],"it":[92],"therefore":[94],"not":[95],"tailored":[96],"particular":[99],"dataset":[100],"or":[101],"language.":[102],"Results":[103],"show":[104],"that":[105],"this":[106],"simple":[107],"approach":[108],"improves":[109],"accuracy":[111,134],"unvoiced":[113],"phonemes":[114],"4%":[116],"within":[117],"5":[119],"ms":[120,127],"margin,":[121],"5%":[123],"10":[126],"margin.":[128],"For":[129],"voiced":[131],"phonemes,":[132],"however,":[133],"drops":[135],"slightly.":[136]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}