{"id":"https://openalex.org/W4375868846","doi":"https://doi.org/10.1109/icassp49357.2023.10095455","title":"Adaptive Time-Scale Modification for Improving Speech Intelligibility Based On Phoneme Clustering For Streaming Services","display_name":"Adaptive Time-Scale Modification for Improving Speech Intelligibility Based On Phoneme Clustering For Streaming Services","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868846","doi":"https://doi.org/10.1109/icassp49357.2023.10095455"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102326713","display_name":"Sohee Jang","orcid":"https://orcid.org/0009-0007-0882-6439"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sohee Jang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101997507","display_name":"Jiye Kim","orcid":"https://orcid.org/0000-0002-2427-8176"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiye Kim","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055626179","display_name":"Yeon-Ju Kim","orcid":"https://orcid.org/0000-0002-2570-750X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeon-Ju Kim","raw_affiliation_strings":["Hanyang University,Department of Artificial Intelligence Application,Seoul,Republic of Korea","Department of Artificial Intelligence Application, Hanyang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Artificial Intelligence Application,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Artificial Intelligence Application, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102326713"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.4135,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5404433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9855999946594238,"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":0.8269158005714417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7486166954040527},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6780744791030884},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5801724791526794},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.479004830121994},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.4729696810245514},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4678797125816345},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.43494829535484314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269158005714417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7486166954040527},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6780744791030884},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5801724791526794},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.479004830121994},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.4729696810245514},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4678797125816345},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.43494829535484314},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2021875505","https://openalex.org/W2098920026","https://openalex.org/W2116428736","https://openalex.org/W2144994235","https://openalex.org/W2168510624","https://openalex.org/W2171321863","https://openalex.org/W2278339107","https://openalex.org/W2747874407","https://openalex.org/W3096831136","https://openalex.org/W4226421894","https://openalex.org/W4231785952","https://openalex.org/W4235716345"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W2346347014"],"abstract_inverted_index":{"Time-scale":[0],"modification":[1,55],"(TSM)":[2],"is":[3],"important":[4],"in":[5],"streaming":[6],"services,":[7],"including":[8],"over-the-top":[9],"(OTT)":[10],"platforms,":[11],"audiobooks,":[12],"and":[13,32,42,84,113],"online":[14],"lectures.":[15],"Although":[16],"TSM":[17],"modifies":[18],"the":[19,30,35,61,99,102,133,137],"speed":[20],"of":[21,34,68,120,126,146],"audio":[22,26,40],"while":[23],"maintaining":[24],"other":[25,150],"attributes":[27],"such":[28],"as":[29],"pitch":[31],"timbre":[33],"speaker,":[36],"it":[37],"unnaturally":[38],"distorts":[39],"signals":[41],"makes":[43],"spoken":[44],"content":[45],"difficult":[46],"to":[47,70],"understand.":[48],"This":[49],"study":[50],"proposes":[51],"an":[52,88],"adaptive":[53,89],"time-scale":[54,85],"algorithm":[56,76,139],"(ATSM);":[57],"that":[58,132,145],"adaptively":[59],"varies":[60],"speaking":[62,90],"rate":[63,91],"for":[64],"each":[65],"phoneme":[66],"cluster":[67],"speech":[69,72,134,142,147],"improve":[71],"intelligibility.":[73],"The":[74,129],"proposed":[75,100,138],"performs":[77],"forced":[78,82],"alignment":[79],"using":[80,87],"Montreal":[81],"aligner":[83],"reconstruction":[86],"based":[92],"on":[93],"dynamic":[94,115],"time":[95,116],"warping.":[96],"To":[97],"validate":[98],"algorithm,":[101],"diagnostic":[103],"rhyme":[104],"test":[105],"(DRT)":[106],"score,":[107],"comparison":[108],"mean":[109],"opinion":[110],"score":[111,119],"(CMOS),":[112],"fast":[114],"warping":[117],"(FastDTW)":[118],"ATSM":[121],"are":[122],"compared":[123],"with":[124,136,149],"those":[125],"conventional":[127],"TSMs.":[128],"results":[130],"show":[131],"compressed":[135,148],"has":[140],"improved":[141],"intelligibility":[143],"than":[144],"algorithms.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
