{"id":"https://openalex.org/W2785994290","doi":"https://doi.org/10.1109/apsipa.2017.8282099","title":"Exploiting imbalanced textual and acoustic data for training prosodically-enhanced RNNLMs","display_name":"Exploiting imbalanced textual and acoustic data for training prosodically-enhanced RNNLMs","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785994290","doi":"https://doi.org/10.1109/apsipa.2017.8282099","mag":"2785994290"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5010628266","display_name":"Michael Hentschel","orcid":"https://orcid.org/0000-0003-3986-5725"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"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":"Michael Hentschel","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Seika-cho, Kyoto, Japan","Nara Institute of Science and Technology, Ikoma, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Seika-cho, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Seika-cho, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Seika-cho, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Seika-cho, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Seika-cho, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Seika-cho, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Seika-cho, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072032804","display_name":"Y\u016bji Matsumoto","orcid":"https://orcid.org/0000-0003-4946-9574"},"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":"Yuji Matsumoto","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"618","last_page":"621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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/perplexity","display_name":"Perplexity","score":0.9314831495285034},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.8464323282241821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8360025882720947},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6968821287155151},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6621356010437012},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6048637628555298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5201706886291504},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44411998987197876},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4364951252937317},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43266937136650085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4129675030708313},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07298889756202698}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9314831495285034},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8464323282241821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360025882720947},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6968821287155151},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6621356010437012},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6048637628555298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5201706886291504},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44411998987197876},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4364951252937317},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43266937136650085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4129675030708313},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07298889756202698},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2738404","https://openalex.org/W179875071","https://openalex.org/W1550452347","https://openalex.org/W1582730572","https://openalex.org/W1631260214","https://openalex.org/W1776720497","https://openalex.org/W1934041838","https://openalex.org/W1999965501","https://openalex.org/W2062093483","https://openalex.org/W2064675550","https://openalex.org/W2066378046","https://openalex.org/W2112882007","https://openalex.org/W2114486181","https://openalex.org/W2130086727","https://openalex.org/W2130416582","https://openalex.org/W2146451076","https://openalex.org/W2169384404","https://openalex.org/W2169998051","https://openalex.org/W2171928131","https://openalex.org/W2259472270","https://openalex.org/W2289121263","https://openalex.org/W2396321837","https://openalex.org/W2402268235","https://openalex.org/W2426479676","https://openalex.org/W2951714314","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W6600113195","https://openalex.org/W6634727054","https://openalex.org/W6636811518","https://openalex.org/W6637804156","https://openalex.org/W6676921367","https://openalex.org/W6680532216","https://openalex.org/W6684930139","https://openalex.org/W6711681208"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"many":[3],"attempts":[4],"in":[5,14,76],"the":[6,43,47,66,69,73,78,90,135],"past":[7],"to":[8,34,95,104],"exploit":[9,97],"various":[10],"sources":[11],"of":[12,37,89],"information":[13,61,71,80],"language":[15,29,110,116],"modelling":[16],"besides":[17],"words,":[18],"for":[19,85,131],"instance":[20],"prosody":[21],"or":[22],"topic":[23],"information.":[24],"With":[25],"neural":[26,44,108],"network":[27,45,109],"based":[28],"models,":[30],"it":[31],"became":[32],"easier":[33],"make":[35],"use":[36],"this":[38,121],"continuous":[39,53],"valued":[40,49,54],"information,":[41],"because":[42],"transforms":[46],"discrete":[48],"space":[50],"into":[51],"a":[52,86,106,115],"space.":[55],"So":[56],"far,":[57],"models":[58],"incorporating":[59],"prosodic":[60],"were":[62],"jointly":[63],"trained":[64],"on":[65,134],"auxiliary":[67,79],"and":[68,99,126],"textual":[70],"from":[72,118],"beginning.":[74],"However,":[75],"practice":[77],"is":[81],"usually":[82],"only":[83],"available":[84],"small":[87],"amount":[88],"training":[91,114],"data.":[92],"In":[93],"order":[94],"fully":[96],"text":[98],"acoustic":[100],"data,":[101],"we":[102,123],"propose":[103],"re-train":[105],"recurrent":[107],"model,":[111],"rather":[112],"than":[113],"model":[117],"scratch.":[119],"Using":[120],"method":[122],"achieved":[124],"perplexity":[125],"word":[127],"error":[128],"rate":[129],"reductions":[130],"N-best":[132],"rescoring":[133],"MIT-OCW":[136],"lecture":[137],"corpus.":[138]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}