{"id":"https://openalex.org/W7214129259","doi":null,"title":"HaikuS2S: A Cascaded System For Responding In Verse","display_name":"HaikuS2S: A Cascaded System For Responding In Verse","publication_year":2026,"publication_date":"2026-09-20","ids":{"openalex":"https://openalex.org/W7214129259"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.23951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.23951","pdf_url":"https://arxiv.org/pdf/2609.23951","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.23951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134269493","display_name":"Devangi Sharma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharma, Devangi","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132686220","display_name":"Sophia Judicke","orcid":"https://orcid.org/0009-0000-9482-8893","observed_orcids":["https://orcid.org/0009-0000-9482-8893"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judicke, Sophia","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152546319","display_name":"Glenda Tan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tan, Glenda","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152552386","display_name":"Conrad Schaumburg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schaumburg, Conrad","raw_affiliation_strings":["Unaffiliated"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unaffiliated","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152551228","display_name":"Shinji Watanabe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Watanabe, Shinji","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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":0.00019999999494757503,"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/haiku","display_name":"haiku","score":0.8930000066757202},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.7649999856948853},{"id":"https://openalex.org/keywords/prosody-transfer","display_name":"prosody transfer","score":0.6819999814033508},{"id":"https://openalex.org/keywords/syllable-structure","display_name":"syllable structure","score":0.5730000138282776},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6169999837875366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.753000020980835},{"id":"https://openalex.org/keywords/cascaded-systems","display_name":"cascade systems","score":0.7519999742507935},{"id":"https://openalex.org/keywords/tonal-alignment","display_name":"tonal alignment","score":0.7730000019073486}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9466999769210815},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6049000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5148000121116638},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4896000027656555},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4876999855041504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4271000027656555},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4047999978065491},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806000053882599},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32199999690055847},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3188999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2609.23951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.23951","pdf_url":"https://arxiv.org/pdf/2609.23951","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.23951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.23951","pdf_url":"https://arxiv.org/pdf/2609.23951","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/W7214129259.pdf","grobid_xml":"https://content.openalex.org/works/W7214129259.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2795109282","https://openalex.org/W4210777104","https://openalex.org/W4296068797","https://openalex.org/W4297841590","https://openalex.org/W4366493008","https://openalex.org/W4402669711"],"related_works":["https://openalex.org/W4297841590","https://openalex.org/W4225303561","https://openalex.org/W7155072721","https://openalex.org/W7161128632","https://openalex.org/W6966872749","https://openalex.org/W4405796221","https://openalex.org/W3104580832","https://openalex.org/W4300437650","https://openalex.org/W4388878577","https://openalex.org/W4285603330"],"abstract_inverted_index":{"Expressive":[0],"speech":[1,56,79],"synthesis":[2],"has":[3],"advanced":[4],"through":[5],"prosody":[6,21,82,91],"modeling,":[7],"yet":[8],"generating":[9],"structured":[10],"poetic":[11],"speech,":[12],"such":[13],"as":[14],"haiku,":[15,62],"remains":[16],"challenging.":[17],"Prior":[18],"work":[19],"on":[20,66,76,105],"transfer":[22],"improves":[23],"expressiveness,":[24],"and":[25,63,69,81,92,109],"fine-tuned":[26,99],"poetry":[27,108],"TTS":[28,64],"(text-to-speech)":[29],"systems":[30],"capture":[31],"verse":[32],"intonation.":[33],"However,":[34],"these":[35],"models":[36],"do":[37],"not":[38],"model":[39],"haiku's":[40],"5-7-5":[41],"syllable":[42],"structure":[43],"or":[44],"line-ending":[45],"pauses.":[46],"We":[47,111],"present":[48],"a":[49],"cascaded":[50],"system,":[51],"HaikuS2S,":[52],"combining":[53],"ASR":[54],"(automatic":[55],"recognition),":[57],"LLM":[58],"(large":[59],"language":[60],"model)-generated":[61],"fine-tuning":[65],"both":[67,106],"prose":[68],"custom":[70],"haiku":[71],"datasets.":[72],"Our":[73],"evaluation":[74],"focuses":[75],"emotion":[77,118],"similarity,":[78],"quality,":[80],"alignment.":[83],"In":[84],"our":[85,90,98],"experiments,":[86],"we":[87,115],"see":[88,113],"that":[89,114],"tonal":[93],"alignment":[94],"improve":[95],"significantly":[96],"with":[97],"systems,":[100],"particularly":[101],"the":[102],"one":[103],"trained":[104],"general":[107],"haiku.":[110],"also":[112],"maintain":[116],"similar":[117],"similarity":[119],"scores":[120],"across":[121],"all":[122],"systems.":[123]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-24T00:00:00"}