{"id":"https://openalex.org/W4415068063","doi":"https://doi.org/10.21437/interspeech.2025-1707","title":"Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM","display_name":"Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415068063","doi":"https://doi.org/10.21437/interspeech.2025-1707"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1707","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.11089","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008353746","display_name":"Jaya Prakash","orcid":"https://orcid.org/0000-0002-2375-154X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jeena Prakash","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101691539","display_name":"B. Vinoth Kumar","orcid":"https://orcid.org/0000-0001-8564-5120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Blessingh Kumar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004977752","display_name":"Kadri Hac\u0131o\u011flu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kadri Hacioglu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067433878","display_name":"Bidisha Sharma","orcid":"https://orcid.org/0000-0002-4195-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bidisha Sharma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071743747","display_name":"Sindhuja Gopalan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sindhuja Gopalan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086802034","display_name":"Malolan Chetlur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malolan Chetlur","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020547781","display_name":"Shankar M. Venkatesan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shankar Venkatesan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114060825","display_name":"Andreas Stolcke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5008353746"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15660725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"579","last_page":"583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/T11309","display_name":"Music and Audio Processing","score":0.9943000078201294,"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/language-model","display_name":"Language model","score":0.5072000026702881},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5062000155448914},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.45329999923706055},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.42089998722076416},{"id":"https://openalex.org/keywords/majority-rule","display_name":"Majority rule","score":0.37880000472068787},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.36970001459121704},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.33980000019073486},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3384999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532800018787384},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C153668964","wikidata":"https://www.wikidata.org/wiki/Q27636","display_name":"Majority rule","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.36970001459121704},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.267300009727478}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1707","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.11089","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11089","pdf_url":"https://arxiv.org/pdf/2506.11089","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2506.11089","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11089","pdf_url":"https://arxiv.org/pdf/2506.11089","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"models":[4,58,107],"rely":[5],"on":[6,22],"high-quality":[7],"transcribed":[8],"data":[9],"for":[10,15,66,108],"effective":[11],"training.":[12],"Generating":[13],"pseudo-labels":[14,97],"large":[16,56],"unlabeled":[17],"audio":[18],"datasets":[19],"often":[20],"relies":[21],"complex":[23],"pipelines":[24],"that":[25],"combine":[26],"multiple":[27,77],"ASR":[28,106],"outputs":[29],"through":[30],"multi-stage":[31],"processing,":[32],"leading":[33],"to":[34,90,103,121],"error":[35],"propagation,":[36],"information":[37],"loss":[38],"and":[39,80,117],"disjoint":[40],"optimization.":[41],"We":[42,71],"propose":[43],"a":[44,73],"unified":[45],"multi-ASR":[46],"prompt-driven":[47],"framework":[48],"using":[49],"postprocessing":[50],"by":[51,99],"either":[52],"textual":[53,116],"or":[54,62],"speech-based":[55],"language":[57],"(LLMs),":[59],"replacing":[60],"voting":[61],"other":[63],"arbitration":[64],"logic":[65],"reconciling":[67],"the":[68,96,100],"ensemble":[69],"outputs.":[70],"perform":[72],"comparative":[74],"study":[75],"of":[76],"architectures":[78],"with":[79,115],"without":[81],"LLMs,":[82],"showing":[83,112],"significant":[84],"improvements":[85],"in":[86],"transcription":[87],"accuracy":[88],"compared":[89,120],"traditional":[91],"methods.":[92],"Furthermore,":[93],"we":[94],"use":[95],"generated":[98],"various":[101],"approaches":[102],"train":[104],"semi-supervised":[105],"different":[109],"datasets,":[110],"again":[111],"improved":[113],"performance":[114],"speechLLM":[118],"transcriptions":[119],"baselines.":[122]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-11T00:00:00"}