{"id":"https://openalex.org/W4415433648","doi":"https://doi.org/10.21437/interspeech.2025-76","title":"Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation","display_name":"Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433648","doi":"https://doi.org/10.21437/interspeech.2025-76"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-76","doi":"https://doi.org/10.21437/interspeech.2025-76","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-76","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.07646","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rui Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101112881","display_name":"Xiaolong Lin","orcid":"https://orcid.org/0009-0006-1197-8348","observed_orcids":["https://orcid.org/0009-0006-1197-8348"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101881764","display_name":"Jiawang Liu","orcid":"https://orcid.org/0000-0003-4167-7504","observed_orcids":["https://orcid.org/0000-0003-4167-7504","https://orcid.org/0009-0002-7107-9732"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shixi Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shixi Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026517700","display_name":"Zhenpeng Zhan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenpeng Zhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22003978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2540","last_page":"2544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-annotation","display_name":"speech annotation","score":0.7559999823570251},{"id":"https://openalex.org/keywords/japanese-speech","display_name":"Japanese speech","score":0.6179999709129333},{"id":"https://openalex.org/keywords/prosodic-annotation","display_name":"prosodic annotation","score":0.8130000233650208},{"id":"https://openalex.org/keywords/whisper","display_name":"Whisper","score":0.6890000104904175},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544000148773193},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6069999933242798},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5529000163078308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5361999869346619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49790000915527344},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-76","doi":"https://doi.org/10.21437/interspeech.2025-76","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-76","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.07646","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07646","pdf_url":"https://arxiv.org/pdf/2506.07646","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.07646","doi":"https://doi.org/10.48550/arxiv.2506.07646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.07646","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.07646","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07646","pdf_url":"https://arxiv.org/pdf/2506.07646","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433648.pdf","grobid_xml":"https://content.openalex.org/works/W4415433648.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2765486990","https://openalex.org/W2969049672","https://openalex.org/W3113850747","https://openalex.org/W4327810158","https://openalex.org/W4400518537","https://openalex.org/W4404399446","https://openalex.org/W4406461672"],"related_works":["https://openalex.org/W4402112357","https://openalex.org/W3114420835","https://openalex.org/W4415433895","https://openalex.org/W4283076240","https://openalex.org/W4414789100","https://openalex.org/W202864720","https://openalex.org/W7084100420","https://openalex.org/W4224932891","https://openalex.org/W152371500","https://openalex.org/W2398172401"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,57],"propose":[4],"a":[5,14,29,59,112],"method":[6,75],"for":[7],"annotating":[8],"phonemic":[9,55],"and":[10,47],"prosodic":[11],"labels":[12,102],"on":[13,38,81],"given":[15],"audio-transcript":[16],"pair,":[17],"aimed":[18],"at":[19],"constructing":[20],"Japanese":[21],"text-to-speech":[22],"(TTS)":[23],"datasets.":[24],"Our":[25],"approach":[26],"involves":[27],"fine-tuning":[28],"large-scale":[30],"pre-trained":[31],"automatic":[32],"speech":[33,94],"recognition":[34],"(ASR)":[35],"model,":[36,99],"conditioned":[37],"ground":[39],"truth":[40],"transcripts,":[41],"to":[42,109],"simultaneously":[43],"output":[44],"phrase-level":[45],"graphemes":[46],"annotation":[48],"labels.":[49],"To":[50],"further":[51],"correct":[52],"errors":[53],"in":[54],"labeling,":[56],"employ":[58],"decoding":[60],"strategy":[61],"that":[62,72,90,110],"utilizes":[63],"dictionary":[64],"prior":[65],"knowledge.":[66],"The":[67,85],"objective":[68],"evaluation":[69,87],"results":[70,88],"demonstrate":[71],"our":[73,105],"proposed":[74],"outperforms":[76],"previous":[77],"approaches":[78],"relying":[79],"solely":[80],"text":[82],"or":[83],"audio.":[84],"subjective":[86],"indicate":[89],"the":[91,97],"naturalness":[92],"of":[93,111],"synthesized":[95],"by":[96],"TTS":[98],"trained":[100,114],"with":[101,115],"annotated":[103],"using":[104],"method,":[106],"is":[107],"comparable":[108],"model":[113],"manual":[116],"annotations.":[117]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-24T00:00:00"}