{"id":"https://openalex.org/W2404738502","doi":"https://doi.org/10.21437/interspeech.2012-194","title":"Text-to-speech intelligibility across speech rates","display_name":"Text-to-speech intelligibility across speech rates","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2404738502","doi":"https://doi.org/10.21437/interspeech.2012-194","mag":"2404738502"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5002689895","display_name":"Ann K. Syrdal","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ann K. Syrdal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091480105","display_name":"H. Timothy Bunnell","orcid":"https://orcid.org/0000-0002-3099-7572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H. Timothy Bunnell","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110881779","display_name":"Susan R. Hertz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Susan R. Hertz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108191538","display_name":"Taniya Mishra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taniya Mishra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083802847","display_name":"Murray F. Spiegel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murray Spiegel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009622382","display_name":"Corine Bickley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Corine Bickley","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040757683","display_name":"Deborah M. Rekart","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deborah Rekart","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001637149","display_name":"Matthew J. Makashay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew J. Makashay","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5002689895"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7685,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87780486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"623","last_page":"626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8587754964828491},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.745650053024292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7142809629440308},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6868051290512085},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6287796497344971},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6146031618118286},{"id":"https://openalex.org/keywords/words-per-minute","display_name":"Words per minute","score":0.5748873353004456},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.48613569140434265},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313865661621094},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.17393815517425537},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17166081070899963},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12300628423690796},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11648011207580566},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08470860123634338}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8587754964828491},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.745650053024292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142809629440308},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6868051290512085},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6287796497344971},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6146031618118286},{"id":"https://openalex.org/C2777970837","wikidata":"https://www.wikidata.org/wiki/Q569389","display_name":"Words per minute","level":3,"score":0.5748873353004456},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.48613569140434265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313865661621094},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.17393815517425537},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17166081070899963},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12300628423690796},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11648011207580566},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08470860123634338},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.306.9507","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.306.9507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.research.att.com/~ttsweb/tts/papers/2012/TTSintel5.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1935012542","https://openalex.org/W1999885698","https://openalex.org/W2045388414","https://openalex.org/W2093696618","https://openalex.org/W2150658333","https://openalex.org/W2168510624","https://openalex.org/W2172102321","https://openalex.org/W2408184471"],"related_works":["https://openalex.org/W234770729","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W19748186","https://openalex.org/W2611973037","https://openalex.org/W2032960563","https://openalex.org/W2142993035"],"abstract_inverted_index":{"A":[0],"web-based":[1],"listening":[2],"test":[3],"measured":[4],"intelligibility":[5],"across":[6,127],"speech":[7,19,66,100,128,151,155],"rate":[8,101,156],"of":[9,14,29,31,106],"8":[10],"TTS":[11,47,115,121,140],"systems":[12,24,122],"and":[13,43,51,94,142],"a":[15,49,52,95],"linearly":[16],"timecompressed":[17],"human":[18,134],"reference":[20],"voice.":[21],"The":[22,117],"synthesis":[23,35],"included":[25],"2":[26,118],"independent":[27],"representatives":[28],"each":[30,46,105],"the":[32,91,114,124],"following":[33],"4":[34],"methods:":[36],"formant,":[37],"diphone":[38],"concatenation,":[39,42],"unit":[40,119],"selection":[41,120],"HMM.":[44],"For":[45],"system,":[48],"female":[50],"male":[53],"American":[54],"English":[55],"voice":[56],"were":[57,62,87,110,123,145],"tested.":[58],"Semantically":[59],"unpredictable":[60],"sentences":[61],"presented":[63],"at":[64,90],"6":[65],"rates":[67],"from":[68],"200":[69],"to":[70,133],"450":[71],"words":[72],"per":[73,99],"minute.":[74],"In":[75],"an":[76],"open":[77],"response":[78],"format,":[79],"listeners":[80],"typed":[81],"what":[82],"they":[83],"heard.":[84],"Listener":[85],"transcriptions":[86],"automatically":[88],"scored":[89],"word":[92],"level,":[93],"normalized":[96],"edit":[97],"distance":[98],"was":[102,131],"calculated":[103],"for":[104],"355":[107],"listeners.":[108],"There":[109],"significant":[111,147],"differences":[112],"among":[113],"systems.":[116],"most":[125],"intelligible":[126],"rates;":[129],"one":[130],"equivalent":[132],"speech.":[135],"Listeners":[136],"\u201f":[137],"native":[138],"language,":[139],"familiarity,":[141],"audio":[143],"equipment":[144],"also":[146],"factors.":[148],"Index":[149],"Terms:":[150],"synthesis,":[152],"text-to-speech,":[153],"intelligibility,":[154]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
