{"id":"https://openalex.org/W4416252209","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228737","title":"Unsupervised Speech Unit Boundary Detection Guided by Linguistic Rule Knowledge","display_name":"Unsupervised Speech Unit Boundary Detection Guided by Linguistic Rule Knowledge","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252209","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228737"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5014452057","display_name":"Sanlong Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanlong Jiang","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068973438","display_name":"Ling Dong","orcid":"https://orcid.org/0000-0003-1612-6671"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Dong","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107954117","display_name":"Wenjun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Wang","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619287","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017471172","display_name":"Shengxiang Gao","orcid":"https://orcid.org/0000-0002-2980-8420"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10660446"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32609258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8809000253677368,"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":0.8809000253677368,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.020999999716877937,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.01489999983459711,"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/syllable","display_name":"Syllable","score":0.580299973487854},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5525000095367432},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5485000014305115},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.482699990272522},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.4530999958515167},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.44350001215934753},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.39959999918937683},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.37389999628067017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595000267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6147000193595886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5846999883651733},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.580299973487854},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5525000095367432},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4381999969482422},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.37389999628067017},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2046932483","https://openalex.org/W2890536590","https://openalex.org/W2954930777","https://openalex.org/W2962799225","https://openalex.org/W2972706021","https://openalex.org/W2995181338","https://openalex.org/W3096656254","https://openalex.org/W3097777922","https://openalex.org/W3170201991","https://openalex.org/W3197974236","https://openalex.org/W3198134274","https://openalex.org/W3204915839","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3209993061","https://openalex.org/W4313182775","https://openalex.org/W4319862670","https://openalex.org/W4372260178","https://openalex.org/W4415800663"],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(UASR)":[4],"aims":[5],"to":[6,35,88,99],"align":[7],"speech":[8,23,129],"signals":[9,93],"with":[10],"corresponding":[11],"text":[12],"without":[13],"relying":[14],"on":[15,53,116],"annotated":[16],"data.":[17],"However,":[18],"the":[19,108,124,138,145],"unknown":[20],"boundaries":[21,39],"of":[22,55,105,140],"units":[24],"pose":[25],"challenges":[26],"for":[27],"cross-modal":[28,134],"alignment,":[29],"and":[30,40,66,83,133],"existing":[31],"methods":[32],"often":[33],"struggle":[34],"accurately":[36],"identify":[37],"these":[38],"capture":[41],"structural":[42,110],"information.":[43],"To":[44],"address":[45],"this,":[46],"we":[47],"propose":[48],"a":[49,101],"reward":[50,90],"model":[51,103],"based":[52],"knowledge":[54,143],"linguistic":[56,142],"rules.":[57],"By":[58],"analyzing":[59],"boundary":[60,131],"structures":[61],"at":[62],"three":[63],"levels\u2014phonemes,":[64],"syllables,":[65],"words\u2014we":[67],"design":[68],"multi-granularity":[69],"scoring":[70],"functions,":[71],"including":[72],"Sequence":[73],"Reasonability":[74],"(SR),":[75],"Syllable":[76],"Legality":[77],"Rules":[78,86],"(SLR),":[79],"Syllable-to-Word":[80],"Evaluation":[81],"(SWE),":[82],"Syntax":[84],"Grammar":[85],"(SGR),":[87],"generate":[89],"signals.":[91],"These":[92],"are":[94],"utilized":[95],"in":[96,112],"reinforcement":[97],"learning":[98],"train":[100],"segmentation":[102],"capable":[104],"effectively":[106,127],"capturing":[107],"latent":[109],"patterns":[111],"speech.":[113],"Experimental":[114],"evaluations":[115],"two":[117],"publicly":[118],"available":[119],"English":[120],"datasets":[121],"demonstrate":[122],"that":[123],"proposed":[125],"method":[126],"improves":[128],"unit":[130],"detection":[132],"alignment":[135],"accuracy,":[136],"validating":[137],"feasibility":[139],"integrating":[141],"into":[144],"UASR":[146],"framework.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}