{"id":"https://openalex.org/W7148434072","doi":"https://doi.org/10.1109/asru65441.2025.11434691","title":"LCS-CTC: Leveraging Soft Alignments to Enhance Phonetic Transcription Robustness","display_name":"LCS-CTC: Leveraging Soft Alignments to Enhance Phonetic Transcription Robustness","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148434072","doi":"https://doi.org/10.1109/asru65441.2025.11434691"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5059789104","display_name":"Zongli Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zongli Ye","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132812774","display_name":"Jiachen Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113428993","display_name":"A. CLARE GUPTA","orcid":"https://orcid.org/0009-0002-1491-1537"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshaj Gupta","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310995","display_name":"Xuanru Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanru Zhou","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129736730","display_name":"Haodong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Li","raw_affiliation_strings":["SUSTech"],"affiliations":[{"raw_affiliation_string":"SUSTech","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Krish Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krish Patel","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011222871","display_name":"H.J. Park","orcid":"https://orcid.org/0009-0009-3283-2892"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hwi Joo Park","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019094940","display_name":"Dingkun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dingkun Zhou","raw_affiliation_strings":["SCUT"],"affiliations":[{"raw_affiliation_string":"SCUT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124946820","display_name":"Chenxu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Guo","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114170893","display_name":"Shuhe Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhe Li","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105516911","display_name":"S. Wang","orcid":"https://orcid.org/0000-0001-7887-1728"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Wang","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132778507","display_name":"Iris Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iris Zhou","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015390421","display_name":"Cheol Jun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheol Jun Cho","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077923985","display_name":"Zoe Ezzes","orcid":null},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Zoe Ezzes","raw_affiliation_strings":["IUCSF"],"affiliations":[{"raw_affiliation_string":"IUCSF","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126722667","display_name":"Jet M.J. Vonk","orcid":null},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Jet M.J. Vonk","raw_affiliation_strings":["IUCSF"],"affiliations":[{"raw_affiliation_string":"IUCSF","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106870223","display_name":"Brittany Morin","orcid":null},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Brittany T. Morin","raw_affiliation_strings":["IUCSF"],"affiliations":[{"raw_affiliation_string":"IUCSF","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026738231","display_name":"Rian Bogley","orcid":null},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Rian Bogley","raw_affiliation_strings":["IUCSF"],"affiliations":[{"raw_affiliation_string":"IUCSF","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132751175","display_name":"Lisa Wauters","orcid":null},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Lisa Wauters","raw_affiliation_strings":["IUCSF"],"affiliations":[{"raw_affiliation_string":"IUCSF","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059104887","display_name":"Zachary Miller","orcid":"https://orcid.org/0000-0002-5991-3053"},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Zachary A. Miller","raw_affiliation_strings":["IUCSF"],"affiliations":[{"raw_affiliation_string":"IUCSF","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113416531","display_name":"Maria Luisa Gorno-Tempini","orcid":null},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Maria Luisa Gorno-Tempini","raw_affiliation_strings":["IUCSF"],"affiliations":[{"raw_affiliation_string":"IUCSF","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132793798","display_name":"Gopala Anumanchipalli","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala Anumanchipalli","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":21,"corresponding_author_ids":["https://openalex.org/A5059789104"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86864042,"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":0.6516000032424927,"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":0.6516000032424927,"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/T10885","display_name":"Gene expression and cancer classification","score":0.047200001776218414,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.04039999842643738,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5428000092506409},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.27070000767707825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26570001244544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912999749183655},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5428000092506409},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48510000109672546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3158000111579895},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21789999306201935},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.210999995470047},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.20389999449253082}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2048347373","https://openalex.org/W2127141656","https://openalex.org/W2138190873","https://openalex.org/W2162744351","https://openalex.org/W2747874407","https://openalex.org/W3097777922","https://openalex.org/W3207272747","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4220963633","https://openalex.org/W4223430326","https://openalex.org/W4224935349","https://openalex.org/W4319442412","https://openalex.org/W4372260274","https://openalex.org/W4385661207","https://openalex.org/W4389518865","https://openalex.org/W4391021769","https://openalex.org/W4391833135","https://openalex.org/W4392902865","https://openalex.org/W4395029390","https://openalex.org/W4402111558","https://openalex.org/W4402115913","https://openalex.org/W4404563387","https://openalex.org/W4406385636","https://openalex.org/W4406461796","https://openalex.org/W4411120560","https://openalex.org/W4411337007","https://openalex.org/W4411630329","https://openalex.org/W4415432636","https://openalex.org/W4415432744","https://openalex.org/W4415432952","https://openalex.org/W4415432955","https://openalex.org/W4415795931"],"related_works":[],"abstract_inverted_index":{"Phonetic":[0],"speech":[1,11,54],"transcription":[2],"is":[3,18],"crucial":[4],"for":[5,23,52],"finegrained":[6],"linguistic":[7],"analysis":[8],"and":[9,40,75,103,112,120,139],"downstream":[10],"applications.":[12],"While":[13],"Connectionist":[14],"Temporal":[15],"Classification":[16],"(CTC)":[17],"a":[19,49,58,64,77],"widely":[20],"used":[21,92],"approach":[22],"such":[24],"tasks":[25],"due":[26],"to":[27,93,133],"its":[28,131],"efficiency,":[29],"it":[30],"often":[31],"falls":[32],"short":[33],"in":[34],"recognition":[35,55,111],"performance,":[36],"especially":[37],"under":[38],"unclear":[39],"nonfluent":[41],"speech.":[42,141],"In":[43],"this":[44],"work,":[45],"we":[46],"propose":[47],"LCS-CTC,":[48],"two-stage":[50],"framework":[51],"phoneme-level":[53],"that":[56,123],"combines":[57],"similarity-aware":[59],"local":[60],"alignment":[61,88],"algorithm":[62],"with":[63],"constrained":[65],"CTC":[66,96,128],"training":[67],"objective.":[68],"By":[69],"predicting":[70],"fine-grained":[71],"frame-phoneme":[72],"cost":[73],"matrices":[74],"applying":[76],"modified":[78],"Longest":[79],"Common":[80],"Subsequence":[81],"(LCS)":[82],"algorithm,":[83],"our":[84],"method":[85],"identifies":[86],"high-confidence":[87],"zones":[89],"which":[90,107],"are":[91],"constrain":[94],"the":[95],"decoding":[97],"path":[98],"space,":[99],"thereby":[100],"reducing":[101],"overfitting":[102],"improving":[104],"generalization":[105],"ability,":[106],"enables":[108],"both":[109,118],"robust":[110],"text-free":[113],"forced":[114],"alignment.":[115],"Experiments":[116],"on":[117],"LibriSpeech":[119],"PPA":[121],"demonstrate":[122],"LCS-CTC":[124],"consistently":[125],"outperforms":[126],"vanilla":[127],"baselines,":[129],"suggesting":[130],"potential":[132],"unify":[134],"phoneme":[135],"modeling":[136],"across":[137],"fluent":[138],"non-fluent":[140]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2026-04-03T00:00:00"}