{"id":"https://openalex.org/W4391021709","doi":"https://doi.org/10.1109/asru57964.2023.10389664","title":"Haha-POD: An Attempt for Laughter-Based Non-Verbal Speaker Verification","display_name":"Haha-POD: An Attempt for Laughter-Based Non-Verbal Speaker Verification","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021709","doi":"https://doi.org/10.1109/asru57964.2023.10389664"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389664","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5049403564","display_name":"Yuke Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Lin","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075605099","display_name":"Xiaoyi Qin","orcid":"https://orcid.org/0000-0003-2521-8084"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Qin","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654008","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0003-4549-6372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628448","display_name":"Guoqing Zhao","orcid":"https://orcid.org/0000-0001-7130-7147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoqing Zhao","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100780143","display_name":"Ming Li","orcid":"https://orcid.org/0009-0009-3842-7337"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.8449479341506958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7101772427558899},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5812373757362366},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5283808708190918},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4296424984931946},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.23258545994758606},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1484604775905609}],"concepts":[{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.8449479341506958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7101772427558899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5812373757362366},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5283808708190918},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4296424984931946},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.23258545994758606},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1484604775905609},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389664","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336618","display_name":"Science and Technology Program of Suzhou","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W105311456","https://openalex.org/W1591607137","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2401684398","https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W2736005052","https://openalex.org/W2742272018","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2889063624","https://openalex.org/W2936733796","https://openalex.org/W2938004196","https://openalex.org/W2963371159","https://openalex.org/W2964269671","https://openalex.org/W2969985801","https://openalex.org/W2972315886","https://openalex.org/W3008104819","https://openalex.org/W3010893827","https://openalex.org/W3024869864","https://openalex.org/W3096730275","https://openalex.org/W3103152812","https://openalex.org/W3158929093","https://openalex.org/W3196244034","https://openalex.org/W3196560414","https://openalex.org/W3197934793","https://openalex.org/W3197970772","https://openalex.org/W4225272619","https://openalex.org/W4225299287","https://openalex.org/W4305009700","https://openalex.org/W4375868885","https://openalex.org/W6638508641","https://openalex.org/W6846187620"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2760111529","https://openalex.org/W4304693785","https://openalex.org/W3081604601","https://openalex.org/W2391280397","https://openalex.org/W4238600753","https://openalex.org/W2103493245","https://openalex.org/W2546089952","https://openalex.org/W2140022733"],"abstract_inverted_index":{"It":[0],"is":[1,25],"widely":[2],"acknowledged":[3],"that":[4,21,116],"discriminative":[5],"representation":[6],"for":[7,141],"speaker":[8,19,32],"verification":[9,33],"can":[10,119,145],"be":[11,146],"extracted":[12],"from":[13,56],"verbal":[14,71,88],"speech.":[15,72],"However,":[16],"how":[17],"much":[18],"information":[20],"non-verbal":[22,41,90],"vocalization":[23],"carries":[24],"still":[26],"a":[27,47,52,76,96,131],"puzzle.":[28],"This":[29],"paper":[30],"explores":[31],"based":[34],"on":[35,134],"the":[36,83,107,122,125,135,142],"most":[37],"ubiquitous":[38],"form":[39],"of":[40,124],"voice,":[42],"laughter.":[43],"First,":[44],"we":[45,74],"use":[46],"semi-automatic":[48],"pipeline":[49],"to":[50,81,105],"collect":[51],"new":[53],"Haha-Pod":[54,94,143],"dataset":[55,61,144],"open-source":[57],"podcast":[58],"media.":[59],"The":[60,139],"contains":[62],"over":[63],"240":[64],"speakers\u2019":[65],"laughter":[66],"clips":[67],"with":[68,129],"corresponding":[69],"high-quality":[70],"Second,":[73],"propose":[75],"Two-Stage":[77],"Teacher-Student":[78],"(2S-TS)":[79],"framework":[80],"minimize":[82],"within-speaker":[84],"embedding":[85],"distance":[86],"between":[87],"and":[89],"(laughter)":[91],"signals.":[92],"Considering":[93],"as":[95],"test":[97,127,137],"set,":[98],"two":[99],"trial":[100],"sets":[101],"(S2L-Eval)":[102],"are":[103],"designed":[104],"verify":[106],"speaker\u2019s":[108],"identity":[109],"through":[110],"laugh":[111],"sounds.":[112],"Experimental":[113],"results":[114],"demonstrate":[115],"our":[117],"method":[118],"significantly":[120],"improve":[121],"performance":[123],"S2L-Eval":[126],"set":[128],"only":[130],"minor":[132],"degradation":[133],"VoxCeleb1":[136],"set.":[138],"resources":[140],"found":[147],"at":[148],"https://github.com/nevermoreLin/HahaPod.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}