{"id":"https://openalex.org/W7203622341","doi":"https://doi.org/10.21437/mlcslm.2026-6","title":"Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge","display_name":"Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7203622341","doi":"https://doi.org/10.21437/mlcslm.2026-6"},"language":"en","primary_location":{"id":"doi:10.21437/mlcslm.2026-6","doi":"https://doi.org/10.21437/mlcslm.2026-6","is_oa":true,"landing_page_url":"https://doi.org/10.21437/mlcslm.2026-6","pdf_url":"https://www.isca-archive.org/mlcslm_2026/shi26_mlcslm.pdf","source":{"id":"https://openalex.org/S7407121150","display_name":"Workshop on Multilingual Conversational Speech Language Model (MLC-SLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2nd Workshop on Multilingual Conversational Speech Language Model (MLC-SLM 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.isca-archive.org/mlcslm_2026/shi26_mlcslm.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102002121","display_name":"Kexin Shi","orcid":"https://orcid.org/0000-0003-1276-1053","observed_orcids":["https://orcid.org/0000-0003-1276-1053"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexin Shi","raw_affiliation_strings":["Ant Group ,","UESTC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group ,","institution_ids":["https://openalex.org/I4405270328"]},{"raw_affiliation_string":"UESTC","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121286861","display_name":"Renhe Sun","orcid":"https://orcid.org/0009-0004-6908-8685","observed_orcids":["https://orcid.org/0009-0004-6908-8685"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renhe Sun","raw_affiliation_strings":["Ant Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group ,","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006016056","display_name":"Yuge Huang","orcid":"https://orcid.org/0000-0001-5387-5992","observed_orcids":["https://orcid.org/0000-0001-5387-5992","https://orcid.org/0009-0005-8552-5950"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuge Huang","raw_affiliation_strings":["Ant Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group ,","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026129964","display_name":"Ximeng Wang","orcid":"https://orcid.org/0000-0002-2445-6737","observed_orcids":["https://orcid.org/0000-0002-2445-6737","https://orcid.org/0000-0002-3943-7184"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ximeng Wang","raw_affiliation_strings":["UESTC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UESTC","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121285708","display_name":"Jiayi Zhou","orcid":"https://orcid.org/0009-0009-4244-5562","observed_orcids":["https://orcid.org/0009-0009-4244-5562","https://orcid.org/0000-0003-4669-4872"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Zhou","raw_affiliation_strings":["Ant Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group ,","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147341623","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0002-5323-5343","observed_orcids":["https://orcid.org/0000-0002-5323-5343"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Liu","raw_affiliation_strings":["Ant Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group ,","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137694457","display_name":"Malu Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Malu Zhang","raw_affiliation_strings":["UESTC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UESTC","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3224,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81721497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.9965999722480774,"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":0.0017000000225380063,"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":0.0008999999845400453,"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/speaker-diarization","display_name":"speaker diarization","score":0.8899999856948853},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.7229999899864197}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7858999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771000266075134},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7261000275611877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6693000197410583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6495000123977661},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338000059127808},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38580000400543213},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/mlcslm.2026-6","doi":"https://doi.org/10.21437/mlcslm.2026-6","is_oa":true,"landing_page_url":"https://doi.org/10.21437/mlcslm.2026-6","pdf_url":"https://www.isca-archive.org/mlcslm_2026/shi26_mlcslm.pdf","source":{"id":"https://openalex.org/S7407121150","display_name":"Workshop on Multilingual Conversational Speech Language Model (MLC-SLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2nd Workshop on Multilingual Conversational Speech Language Model (MLC-SLM 2026)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.14150","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14150","pdf_url":"https://arxiv.org/pdf/2608.14150","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.14150","doi":"https://doi.org/10.48550/arxiv.2608.14150","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14150","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.21437/mlcslm.2026-6","doi":"https://doi.org/10.21437/mlcslm.2026-6","is_oa":true,"landing_page_url":"https://doi.org/10.21437/mlcslm.2026-6","pdf_url":"https://www.isca-archive.org/mlcslm_2026/shi26_mlcslm.pdf","source":{"id":"https://openalex.org/S7407121150","display_name":"Workshop on Multilingual Conversational Speech Language Model (MLC-SLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2nd Workshop on Multilingual Conversational Speech Language Model (MLC-SLM 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203622341.pdf","grobid_xml":"https://content.openalex.org/works/W7203622341.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2338908902","https://openalex.org/W4400717319","https://openalex.org/W4409051416","https://openalex.org/W4415255153","https://openalex.org/W6910746321","https://openalex.org/W6948369276","https://openalex.org/W7125811016"],"related_works":["https://openalex.org/W7167937205","https://openalex.org/W7214223884","https://openalex.org/W7221047669","https://openalex.org/W7220926279","https://openalex.org/W7212265258","https://openalex.org/W7168410928","https://openalex.org/W7084080286","https://openalex.org/W7220917498","https://openalex.org/W7084133641","https://openalex.org/W4415432973"],"abstract_inverted_index":{"The":[0],"second":[1],"Multilingual":[2],"Conversational":[3],"Speech":[4],"Language":[5],"Model":[6],"(MLC-SLM)":[7],"Challenge":[8],"evaluates":[9],"two":[10],"tasks":[11],"over":[12],"complete,":[13],"unsegmented":[14],"multilingual":[15],"conversations:":[16],"speaker":[17,35],"diarization":[18],"and":[19,23,39,59,80,83,102,118],"recognition":[20],"(Task":[21,27],"1)":[22],"conversational":[24],"speech":[25],"understanding":[26],"2).Neither":[28],"task":[29],"provides":[30,42],"oracle":[31],"utterance":[32],"boundaries":[33],"or":[34],"labels":[36],"at":[37],"evaluation,":[38],"Task":[40,47,67,91,110],"2":[41,111],"no":[43],"question-answer":[44,72],"training":[45,65],"set.For":[46],"1,":[48],"we":[49,69],"fine-tune":[50,84],"VibeVoice-ASR-7B":[51],"with":[52],"random":[53],"leading-silence":[54],"cropping,":[55],"consistent":[56],"timestamp":[57],"correction,":[58],"an":[60],"exponential":[61],"moving":[62],"average":[63],"(EMA)":[64],"strategy.For":[66],"2,":[68],"construct":[70],"synthetic":[71],"pairs":[73],"through":[74],"multimodal":[75],"candidate":[76],"generation,":[77],"silent-audio":[78],"filtering,":[79],"distribution-matched":[81,116],"augmentation,":[82],"Qwen3-Omni-30B-A3B-Instruct":[85],"for":[86],"tagged":[87,119],"direct":[88,120],"answering.On":[89],"the":[90,109],"1":[92],"evaluation":[93,112],"set,":[94,113],"cropping":[95],"reduces":[96,105],"tcpMER":[97],"from":[98,124],"18.30%":[99],"to":[100,107,126],"17.27%,":[101],"EMA":[103],"further":[104],"it":[106],"16.73%.On":[108],"jointly":[114],"applying":[115],"augmentation":[117],"answering":[121],"raises":[122],"accuracy":[123],"83.0%":[125],"86.0%.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-18T00:00:00"}