{"id":"https://openalex.org/W4402111992","doi":"https://doi.org/10.21437/interspeech.2024-768","title":"Lightweight Transducer Based on Frame-Level Criterion","display_name":"Lightweight Transducer Based on Frame-Level Criterion","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111992","doi":"https://doi.org/10.21437/interspeech.2024-768"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-768","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.13698","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011133553","display_name":"Genshun Wan","orcid":"https://orcid.org/0000-0002-5813-9430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Genshun Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073968947","display_name":"M. L. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengzhi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106912702","display_name":"Tingzhi Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingzhi Mao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442516","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0001-9999-1358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112927758","display_name":"Zhongfu Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongfu Ye","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12169","display_name":"Non-Destructive Testing Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12169","display_name":"Non-Destructive Testing Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9962000250816345,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.9131333827972412},{"id":"https://openalex.org/keywords/blank","display_name":"Blank","score":0.8622667789459229},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6996244788169861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6985375285148621},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6517603993415833},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4274408221244812},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39943569898605347},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.293770432472229},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16194400191307068},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.062137067317962646}],"concepts":[{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.9131333827972412},{"id":"https://openalex.org/C2778089247","wikidata":"https://www.wikidata.org/wiki/Q368951","display_name":"Blank","level":2,"score":0.8622667789459229},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6996244788169861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985375285148621},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6517603993415833},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4274408221244812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39943569898605347},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.293770432472229},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16194400191307068},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.062137067317962646},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-768","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.13698","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.13698","pdf_url":"https://arxiv.org/pdf/2409.13698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.13698","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.13698","pdf_url":"https://arxiv.org/pdf/2409.13698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7900000214576721,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111992.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2361638505","https://openalex.org/W1993662208","https://openalex.org/W2370352440","https://openalex.org/W2009954581","https://openalex.org/W4296141694","https://openalex.org/W2379220204","https://openalex.org/W3160305016","https://openalex.org/W2005071119","https://openalex.org/W3158546193","https://openalex.org/W4249926107"],"abstract_inverted_index":{"The":[0],"transducer":[1,26,134],"model":[2,27],"trained":[3],"based":[4,28],"on":[5,29,125],"sequence-level":[6],"criterion":[7],"requires":[8],"a":[9,24],"lot":[10],"of":[11,17,36,95,116,150],"memory":[12,87],"due":[13],"to":[14,42,73,120,135,139,146,155],"the":[15,18,34,37,44,50,57,61,71,78,82,93,103,107,114,117,121,126,132,148],"generation":[16],"large":[19],"probability":[20,149],"matrix.":[21],"We":[22],"proposed":[23],"lightweight":[25,133],"frame-level":[30],"criterion,":[31],"which":[32],"uses":[33],"results":[35,138,154],"CTC":[38],"forced":[39],"alignment":[40],"algorithm":[41],"determine":[43],"label":[45],"for":[46],"each":[47,67,74],"frame.":[48],"Then":[49],"encoder":[51,72],"output":[52,59,69,76],"can":[53],"be":[54],"combined":[55],"with":[56],"decoder":[58,79],"at":[60],"corresponding":[62],"time,":[63],"rather":[64],"than":[65],"adding":[66],"element":[68,75],"by":[70,77,99],"as":[80],"in":[81,102],"transducer.":[83,140,156],"This":[84],"significantly":[85],"reduces":[86],"and":[88,109,112],"computation":[89],"requirements.":[90],"To":[91],"address":[92],"problem":[94],"imbalanced":[96],"classification":[97],"caused":[98],"excessive":[100],"blanks":[101],"label,":[104],"we":[105,142],"decouple":[106],"blank":[108,118],"non-blank":[110],"probabilities":[111],"truncate":[113],"gradient":[115],"classifier":[119],"main":[122],"network.":[123],"Experiments":[124],"AISHELL-1":[127],"demonstrate":[128],"that":[129],"this":[130],"enables":[131],"achieve":[136],"similar":[137],"Additionally,":[141],"use":[143],"richer":[144],"information":[145],"predict":[147],"blank,":[151],"achieving":[152],"superior":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
