{"id":"https://openalex.org/W4405709396","doi":"https://doi.org/10.1109/iscslp63861.2024.10800077","title":"Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets","display_name":"Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709396","doi":"https://doi.org/10.1109/iscslp63861.2024.10800077"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"article","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/A5102662617","display_name":"Xuelong Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuelong Geng","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076135351","display_name":"Tianyi Xu","orcid":"https://orcid.org/0000-0003-4197-8163"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Xu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649112","display_name":"Kun Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wei","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072425459","display_name":"Bingshen Mu","orcid":"https://orcid.org/0009-0009-7797-865X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingshen Mu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014632942","display_name":"Hongfei Xue","orcid":"https://orcid.org/0000-0001-9691-9668"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Xue","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808140","display_name":"Wang He","orcid":"https://orcid.org/0000-0002-3436-1299"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104231255","display_name":"Yangze Li","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangze Li","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114198820","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0008-7069-979X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109714651","display_name":"Yuhang Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Dai","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113203405","display_name":"Longhao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longhao Li","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061421623","display_name":"Mingchen Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingchen Shao","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5102662617"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":3.9792,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94578399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7587000131607056,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.7587000131607056,"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/open-source","display_name":"Open source","score":0.7900204062461853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6731318831443787},{"id":"https://openalex.org/keywords/open-source-software","display_name":"Open source software","score":0.4697195589542389},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16564607620239258},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1632956564426422}],"concepts":[{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.7900204062461853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6731318831443787},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.4697195589542389},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16564607620239258},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1632956564426422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2905678190","https://openalex.org/W2939111082","https://openalex.org/W2943845043","https://openalex.org/W2963242190","https://openalex.org/W2972625221","https://openalex.org/W3196117288","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W4283067311","https://openalex.org/W4375868856","https://openalex.org/W4389524500","https://openalex.org/W4391021666","https://openalex.org/W4393178509","https://openalex.org/W6629717138","https://openalex.org/W6739901393","https://openalex.org/W6754473786","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6772129282","https://openalex.org/W6796581206","https://openalex.org/W6797037654","https://openalex.org/W6803334173","https://openalex.org/W6810571346","https://openalex.org/W6846305509","https://openalex.org/W6847363464","https://openalex.org/W6848208918","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851513886","https://openalex.org/W6853249747","https://openalex.org/W6854445763","https://openalex.org/W6855793536","https://openalex.org/W6857054612","https://openalex.org/W6859099255","https://openalex.org/W6860041859","https://openalex.org/W6861626678","https://openalex.org/W6862410459"],"related_works":["https://openalex.org/W4376877853","https://openalex.org/W1493891899","https://openalex.org/W4250928611","https://openalex.org/W166480398","https://openalex.org/W1612808768","https://openalex.org/W167327709","https://openalex.org/W1977393088","https://openalex.org/W4387839566","https://openalex.org/W4210922265","https://openalex.org/W2288962794"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"un-paralleled":[6],"effectiveness":[7],"in":[8,63,129],"various":[9,54],"NLP":[10],"tasks,":[11],"and":[12,60,90,116,133,154,161],"integrating":[13],"LLMs":[14],"with":[15],"automatic":[16],"speech":[17,57,68],"recognition":[18],"(ASR)":[19],"is":[20],"becoming":[21],"a":[22,40,76],"mainstream":[23],"paradigm.":[24,72],"Building":[25],"upon":[26],"this":[27,37,96],"momentum,":[28],"our":[29,46],"research":[30,47,128],"delves":[31],"into":[32,136],"an":[33,123],"in-depth":[34],"examination":[35],"of":[36,53,56,66,95,102],"paradigm":[38],"on":[39,112],"large":[41],"open-source":[42],"Chinese":[43,140],"dataset.":[44],"Specifically,":[45],"aims":[48],"to":[49,82,87,107,164],"evaluate":[50],"the":[51,64,67,84,99,109,113],"impact":[52],"configurations":[55],"encoders,":[58],"LLMs,":[59],"projector":[61],"modules":[62],"context":[65],"foundation":[69,125],"encoder-LLM":[70],"ASR":[71,103,131],"Furthermore,":[73],"we":[74],"introduce":[75],"three-stage":[77],"training":[78,162],"approach,":[79,97],"expressly":[80],"developed":[81],"enhance":[83],"model's":[85],"ability":[86],"align":[88],"auditory":[89],"textual":[91],"information.":[92],"The":[93],"implementation":[94],"along-side":[98],"strategic":[100],"integration":[101],"components,":[104],"enabled":[105],"us":[106],"achieve":[108],"SOTA":[110],"performance":[111,138],"AISHELL-1,":[114],"Test_Net,":[115],"Test_Meeting":[117],"test":[118],"sets.":[119],"Our":[120],"analysis":[121],"presents":[122],"empirical":[124],"for":[126,149],"future":[127],"LLM-based":[130],"systems":[132],"offers":[134],"insights":[135],"optimizing":[137],"using":[139],"datasets.":[141],"We":[142],"will":[143],"publicly":[144],"release":[145],"all":[146],"scripts":[147],"used":[148],"data":[150],"preparation,":[151],"training,":[152],"inference,":[153],"scoring,":[155],"as":[156,158],"well":[157],"pre-trained":[159],"models":[160],"logs":[163],"promote":[165],"reproducible":[166],"research.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}