{"id":"https://openalex.org/W4415432619","doi":"https://doi.org/10.21437/interspeech.2025-2746","title":"SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment","display_name":"SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432619","doi":"https://doi.org/10.21437/interspeech.2025-2746"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2746","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2746","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.02220","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112980303","display_name":"SooHwan Eom","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"SooHwan Eom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","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":"3573","last_page":"3577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9847000241279602,"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":0.9847000241279602,"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":0.983299970626831,"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/T12031","display_name":"Speech and dialogue systems","score":0.9768999814987183,"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/monotonic-function","display_name":"Monotonic function","score":0.4578000009059906},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31709998846054077},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.28439998626708984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26840001344680786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5922999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5249999761581421},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24549999833106995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23759999871253967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-2746","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2746","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:2606.02220","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.02220","pdf_url":"https://arxiv.org/pdf/2606.02220","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.02220","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02220","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.02220","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.02220","pdf_url":"https://arxiv.org/pdf/2606.02220","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1931183695","display_name":null,"funder_award_id":"RS-2022-II220184","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4805667441","display_name":null,"funder_award_id":"UD230017TD","funder_id":"https://openalex.org/F4320334874","funder_display_name":"Defense Acquisition Program Administration"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,55,113],"representation":[2],"learning":[3],"has":[4],"made":[5],"significant":[6],"progress":[7],"through":[8],"Siamese":[9,46],"networks,":[10],"which":[11],"leverage":[12],"different":[13,36],"views":[14],"of":[15,74],"the":[16,30,75],"same":[17,76],"input.":[18],"However,":[19],"existing":[20],"methods":[21],"often":[22],"require":[23],"frame-wise":[24,89],"alignment":[25],"between":[26,70],"these":[27],"views,":[28],"overlooking":[29],"broader":[31],"linguistic":[32],"context":[33],"invariance":[34],"across":[35],"speaking":[37,118],"styles.":[38],"We":[39],"introduce":[40],"SiamCTC,":[41],"a":[42],"framework":[43],"that":[44,107],"integrates":[45],"networks":[47],"with":[48],"Connectionist":[49],"Temporal":[50],"Classification":[51],"(CTC)":[52],"to":[53,65,98,110],"learn":[54],"representations":[56],"without":[57],"strict":[58],"frame-level":[59],"correspondence.":[60],"By":[61],"employing":[62],"CTC":[63],"loss":[64],"establish":[66],"flexible,":[67],"monotonic":[68],"alignments":[69],"differing":[71],"temporal":[72,84,93],"realizations":[73],"content,":[77],"SiamCTC":[78,108],"accommodates":[79],"speed":[80],"perturbations":[81],"and":[82,95],"other":[83],"augmentations.":[85],"This":[86],"design":[87],"relaxes":[88],"constraints":[90],"while":[91],"preserving":[92],"coherence":[94],"enhancing":[96],"robustness":[97],"speaking-rate":[99],"variations":[100],"in":[101],"downstream":[102],"tasks.":[103],"Our":[104],"experiments":[105],"demonstrate":[106],"leads":[109],"more":[111],"adaptable":[112],"representations,":[114],"particularly":[115],"at":[116],"diverse":[117],"rates.":[119]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}