{"id":"https://openalex.org/W4416034926","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.424","title":"InteractSpeech: A Speech Dialogue Interaction Corpus for Spoken Dialogue Model","display_name":"InteractSpeech: A Speech Dialogue Interaction Corpus for Spoken Dialogue Model","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034926","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.424"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.424","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.424","pdf_url":"https://aclanthology.org/2025.findings-emnlp.424.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.424.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072936428","display_name":"Y.W. Chen","orcid":"https://orcid.org/0000-0003-2566-018X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifu Chen","raw_affiliation_strings":["Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I168879160","https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904447","display_name":"Shengpeng Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengpeng Ji","raw_affiliation_strings":["Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I168879160","https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033874080","display_name":"Ziqing Wang","orcid":"https://orcid.org/0000-0001-8791-0805"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqing Wang","raw_affiliation_strings":["Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I168879160","https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072365834","display_name":"Hanting Wang","orcid":"https://orcid.org/0000-0003-2761-577X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanting Wang","raw_affiliation_strings":["Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I168879160","https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University Zhejiang University Beijing University Of Technology Zhejiang University Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I168879160","https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.15761914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8024","last_page":"8033"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9483000040054321,"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/T12031","display_name":"Speech and dialogue systems","score":0.9483000040054321,"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":0.01119999960064888,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.006899999920278788,"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/feature","display_name":"Feature (linguistics)","score":0.32269999384880066},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.28859999775886536},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.2818000018596649}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5467000007629395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5303999781608582},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37139999866485596},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28060001134872437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.424","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.424","pdf_url":"https://aclanthology.org/2025.findings-emnlp.424.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.424","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.424","pdf_url":"https://aclanthology.org/2025.findings-emnlp.424.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1101031052","display_name":null,"funder_award_id":"U24A20326","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034926.pdf","grobid_xml":"https://content.openalex.org/works/W4416034926.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spoken":[0],"Dialogue":[1],"Models":[2],"(SDMs)":[3],"have":[4],"achieved":[5],"significant":[6,22],"progress":[7],"in":[8,17,145],"recent":[9],"years,":[10],"yet":[11],"they":[12],"continue":[13],"to":[14,37,55],"face":[15],"challenges":[16],"handling":[18,67],"nuanced":[19,61],"interactional":[20,136],"phenomena.A":[21],"bottleneck":[23],"hindering":[24],"further":[25],"advancement":[26],"is":[27],"the":[28,142],"scarcity":[29],"of":[30,149],"publicly":[31],"available,":[32],"highquality":[33],"datasets":[34],"meticulously":[35],"designed":[36,54],"train":[38],"and":[39,69,83,97,152],"evaluate":[40],"these":[41],"fine-grained":[42],"interactive":[43,75,90],"capabilities.We":[44],"introduce":[45],"InteractSpeech,":[46],"a":[47,105,116,128],"150-hour":[48],"English":[49],"speech":[50,81,129],"interaction":[51,63,109],"dialogue":[52,58,101],"dataset":[53,92],"empower":[56],"spoken":[57,87],"models":[59,147],"with":[60],"real-time":[62],"capabilities,":[64],"such":[65],"as":[66],"interruptions":[68],"backchannels.InteractSpeech":[70],"was":[71],"created":[72],"by":[73,84,104,114,126],"synthesizing":[74],"dialogues":[76,88],"from":[77,139],"text":[78],"using":[79],"advanced":[80],"synthesis,":[82],"filtering":[85],"real-world":[86],"for":[89,99,108],"segments.The":[91],"features":[93],"precise":[94],"speaker":[95],"timestamps":[96],"annotations":[98],"diverse":[100],"interactions,":[102],"underpinned":[103],"formal":[106],"framework":[107],"dynamics.We":[110],"demonstrate":[111],"InteractSpeech's":[112],"utility":[113],"fine-tuning":[115],"LLaMA":[117],"3-8B":[118],"model":[119,131],"on":[120],"its":[121],"textual":[122],"scenarios":[123],"and,":[124],"crucially,":[125],"training":[127],"understanding":[130],"that":[132],"accurately":[133],"classifies":[134],"key":[135],"events":[137],"directly":[138],"audio.This":[140],"highlights":[141],"dataset's":[143],"value":[144],"developing":[146],"capable":[148],"more":[150],"natural":[151],"responsive":[153],"conversational":[154],"turntaking.Audio":[155],"samples":[156],"are":[157],"available":[158],"at":[159],"https:":[160],"//interactspeech.github.io/.":[161]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}