{"id":"https://openalex.org/W2937346665","doi":"https://doi.org/10.1109/icassp.2019.8682764","title":"Cross-lingual Speech-based Tobi Label Generation Using Bidirectional Lstm","display_name":"Cross-lingual Speech-based Tobi Label Generation Using Bidirectional Lstm","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937346665","doi":"https://doi.org/10.1109/icassp.2019.8682764","mag":"2937346665"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5069201131","display_name":"Marco Vetter","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Marco Vetter","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069201131"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63827352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":"2017","issue":null,"first_page":"6620","last_page":"6624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.996399998664856,"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/T12031","display_name":"Speech and dialogue systems","score":0.9940000176429749,"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":0.7300925850868225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7029780745506287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3661206364631653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300925850868225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7029780745506287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3661206364631653}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W28194048","https://openalex.org/W30677081","https://openalex.org/W37526647","https://openalex.org/W162654330","https://openalex.org/W746375014","https://openalex.org/W1524333225","https://openalex.org/W1602926290","https://openalex.org/W1979679014","https://openalex.org/W1991148915","https://openalex.org/W2026858810","https://openalex.org/W2100768664","https://openalex.org/W2121997342","https://openalex.org/W2164274485","https://openalex.org/W2166317648","https://openalex.org/W2180044023","https://openalex.org/W2291963065","https://openalex.org/W2294206829","https://openalex.org/W2483390977","https://openalex.org/W2514012605","https://openalex.org/W2620638943","https://openalex.org/W2995508875","https://openalex.org/W3194996120","https://openalex.org/W3217769081","https://openalex.org/W4300939116","https://openalex.org/W4390926476","https://openalex.org/W6601083237","https://openalex.org/W6601230047","https://openalex.org/W6601563604","https://openalex.org/W6606697926","https://openalex.org/W6631362777","https://openalex.org/W6675022971","https://openalex.org/W6738767006","https://openalex.org/W6771771678"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"In":[0],"this":[1,60],"paper":[2],"we":[3,62],"investigate":[4],"the":[5,17,25,43,55,66,86,100,122],"automatic":[6,26],"generation":[7],"of":[8,19,102,124,134,144],"ToBI-style":[9],"prosody":[10],"labels.":[11],"The":[12,108],"work":[13],"is":[14,39],"motivated":[15],"by":[16],"idea":[18],"using":[20,84,112,127],"prosodic":[21,44,138],"information":[22,53,94],"to":[23,48,64],"facilitate":[24],"lexicon":[27],"discovery":[28],"for":[29,34,136],"unseen":[30],"and":[31],"under-resourced":[32],"languages":[33],"which":[35],"sufficient":[36],"training":[37,77],"data":[38],"not":[40,74],"available.":[41],"Specifically,":[42],"boundaries":[45],"are":[46,110],"meant":[47],"serve":[49],"as":[50,89],"additional":[51,93],"top-down":[52],"in":[54,76,99],"word":[56,106],"segmentation":[57],"step.":[58],"To":[59],"end":[61],"attempt":[63],"apply":[65],"trained":[67,115],"Japanese":[68,118],"models":[69],"cross-lingually":[70],"on":[71,116],"a":[72,142],"language":[73],"seen":[75],"(English).":[78],"We":[79,120],"generate":[80],"break":[81,139],"index":[82],"labels,":[83],"only":[85],"speech":[87],"signal":[88],"input,":[90],"with":[91,130],"no":[92],"given":[95],"at":[96],"test":[97],"time":[98],"form":[101],"transcripts":[103],"or":[104],"prior":[105],"segmentations.":[107],"labels":[109,126],"generated":[111],"bidirectional":[113],"LSTMs":[114],"spontaneous":[117],"speech.":[119],"evaluate":[121],"quality":[123],"these":[125],"established":[128],"metrics,":[129],"an":[131],"F1":[132],"score":[133],"0.55":[135],"cross-lingual":[137],"detection":[140],"(given":[141],"tolerance":[143],"80":[145],"ms).":[146]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}