{"id":"https://openalex.org/W7166812112","doi":"https://doi.org/10.18653/v1/2026.acl-long.1997","title":"Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception","display_name":"Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166812112","doi":"https://doi.org/10.18653/v1/2026.acl-long.1997"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1997","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1997","pdf_url":"https://aclanthology.org/2026.acl-long.1997.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1997.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139771075","display_name":"Zhen Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139762954","display_name":"Chao-Han Huck Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139813046","display_name":"Jinchuan Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinchuan Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058387246","display_name":"Hanrong Ye","orcid":"https://orcid.org/0000-0002-7986-6143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanrong Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139823888","display_name":"Ankita Pasad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankita Pasad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031240854","display_name":"Arushi Goel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arushi Goel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020411666","display_name":"Ryo Hachiuma","orcid":"https://orcid.org/0000-0001-8274-3710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryo Hachiuma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139727282","display_name":"Shizhe Diao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shizhe Diao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073181369","display_name":"Kunal Dhawan","orcid":"https://orcid.org/0000-0002-5276-2475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunal Dhawan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784465","display_name":"Sreyan Ghosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123108493","display_name":"Yusuke Hirota","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Hirota","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139800666","display_name":"Zhehuai Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127840447","display_name":"Rafael Valle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael Valle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139852273","display_name":"Chenhui Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139833411","display_name":"Shinji Watanabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139751344","display_name":"Boris Ginsburg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139736860","display_name":"Yu-Chiang Frank Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Chiang Frank Wang","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":0.86256622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"43124","last_page":"43142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.17389999330043793,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.17389999330043793,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.1695999950170517,"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/T12031","display_name":"Speech and dialogue systems","score":0.1363999992609024,"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/perception","display_name":"Perception","score":0.5807999968528748},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4431999921798706},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39820000529289246},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.32710000872612},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.3253999948501587},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.3052999973297119}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.63919997215271},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5807999968528748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5174999833106995},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.39239999651908875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34040001034736633},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.32710000872612},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1997","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1997","pdf_url":"https://aclanthology.org/2026.acl-long.1997.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1997","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1997","pdf_url":"https://aclanthology.org/2026.acl-long.1997.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7504209280014038}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327550","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166812112.pdf","grobid_xml":"https://content.openalex.org/works/W7166812112.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zhen":[0],"Wan,":[1],"Chao-Han":[2],"Huck":[3],"Yang,":[4],"Jinchuan":[5],"Tian,":[6],"Hanrong":[7],"Ye,":[8],"Ankita":[9],"Pasad,":[10],"Szu-Wei":[11],"Fu,":[12],"Arushi":[13],"Goel,":[14],"Ryo":[15],"Hachiuma,":[16],"Shizhe":[17],"Diao,":[18],"Kunal":[19],"Dhawan,":[20],"Sreyan":[21],"Ghosh,":[22],"Yusuke":[23],"Hirota,":[24],"Zhehuai":[25],"Chen,":[26],"Rafael":[27],"Valle,":[28],"Chenhui":[29],"Chu,":[30],"Shinji":[31],"Watanabe,":[32],"Boris":[33],"Ginsburg,":[34],"Yu-Chiang":[35],"Frank":[36],"Wang.":[37],"Proceedings":[38],"of":[39,44],"the":[40,45],"64th":[41],"Annual":[42],"Meeting":[43],"Association":[46],"for":[47],"Computational":[48],"Linguistics":[49],"(Volume":[50],"1:":[51],"Long":[52],"Papers).":[53],"2026.":[54]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
