{"id":"https://openalex.org/W2004255765","doi":"https://doi.org/10.1109/icassp.2013.6639214","title":"A fast table lookup based, statistical model driven non-uniform unit selection TTS","display_name":"A fast table lookup based, statistical model driven non-uniform unit selection TTS","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2004255765","doi":"https://doi.org/10.1109/icassp.2013.6639214","mag":"2004255765"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Speech Group, Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Speech Group, Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank. K. Soong","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027417569","display_name":"Xiaobo Zhou","orcid":"https://orcid.org/0000-0002-4346-9349"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhou","raw_affiliation_strings":["Speech Group, Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Speech Group, Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003241968","display_name":"Yundi Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yundi Qian","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Speech Group, Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Speech Group, Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114860163","display_name":"Xiaotian Zhang","orcid":"https://orcid.org/0000-0003-0574-4095"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotian Zhang","raw_affiliation_strings":["Speech Group, Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Speech Group, Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100342006"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06925911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"7957","last_page":"7961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.8171963691711426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7244045734405518},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.6282798051834106},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5245469212532043},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4856042265892029},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.48187312483787537},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.46331357955932617},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.42798054218292236},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40444129705429077},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17998316884040833},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.17213132977485657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16503751277923584}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8171963691711426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7244045734405518},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.6282798051834106},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5245469212532043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4856042265892029},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.48187312483787537},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.46331357955932617},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.42798054218292236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40444129705429077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17998316884040833},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.17213132977485657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16503751277923584},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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":28,"referenced_works":["https://openalex.org/W123537345","https://openalex.org/W1496562625","https://openalex.org/W1512429158","https://openalex.org/W1514737389","https://openalex.org/W1568585903","https://openalex.org/W1600722501","https://openalex.org/W1887401733","https://openalex.org/W1963627370","https://openalex.org/W1965555277","https://openalex.org/W1973766695","https://openalex.org/W1992287499","https://openalex.org/W2000513720","https://openalex.org/W2024093103","https://openalex.org/W2049686551","https://openalex.org/W2096765209","https://openalex.org/W2111194146","https://openalex.org/W2114010348","https://openalex.org/W2129142580","https://openalex.org/W2291159692","https://openalex.org/W2403964578","https://openalex.org/W3142087749","https://openalex.org/W6630838124","https://openalex.org/W6656576186","https://openalex.org/W6674201379","https://openalex.org/W6676358011","https://openalex.org/W6696355820","https://openalex.org/W6713484195","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W2144265691","https://openalex.org/W1605991620","https://openalex.org/W113683524","https://openalex.org/W4387251676","https://openalex.org/W4385261619","https://openalex.org/W93624718"],"abstract_inverted_index":{"For":[0],"multi-channel":[1],"TTS":[2,41,46,143],"applications,":[3],"e.g.":[4],"in":[5,20,107],"a":[6,28,58,65,89,141],"cloud":[7],"service,":[8],"it":[9],"is":[10,55,105],"highly":[11],"desirable":[12],"that":[13,43,129],"high":[14,142],"quality":[15],"speech":[16],"can":[17,133],"be":[18],"synthesized":[19],"low":[21],"complexity.":[22],"In":[23,45,77],"this":[24],"paper,":[25],"we":[26],"propose":[27],"fast":[29],"table":[30,63,66,122],"lookup":[31],"based,":[32],"statistical":[33],"model":[34],"driven":[35],"approach":[36,132],"to":[37,87],"non-uniform":[38,82],"unit":[39],"selection":[40],"for":[42,67,123],"purpose.":[44],"training,":[47],"the":[48,95,102,108,112,120,130,136],"voice":[49,144],"font":[50],"of":[51,71],"all":[52,72],"waveform":[53,79],"segments":[54,80],"organized":[56],"as":[57],"Gaussian":[59,96],"kernel":[60,97],"coded":[61,98],"hash":[62,99],"and":[64,101],"storing":[68],"quantized":[69],"costs":[70],"possible":[73,124],"concatenation":[74,114],"segment":[75],"pairs.":[76],"synthesis,":[78],"with":[81],"lengths":[83],"are":[84,117],"first":[85],"selected":[86],"construct":[88],"candidate":[90],"lattice":[91,109],"by":[92,110],"looking":[93],"up":[94],"table,":[100],"best":[103],"path":[104],"searched":[106],"minimizing":[111],"accumulated":[113],"scores,":[115],"which":[116],"retrieved":[118],"from":[119],"quantization":[121],"concatenations.":[125],"Experimental":[126],"results":[127],"show":[128],"new":[131],"significantly":[134],"reduce":[135],"search":[137],"complexity":[138],"while":[139],"keep":[140],"quality.":[145]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}