{"id":"https://openalex.org/W4406461643","doi":"https://doi.org/10.1109/slt61566.2024.10832327","title":"Advancing CTC Models for Better Speech Alignment: A Topological Approach","display_name":"Advancing CTC Models for Better Speech Alignment: A Topological Approach","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461643","doi":"https://doi.org/10.1109/slt61566.2024.10832327"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/f7d19ea6-2fb9-4dce-9ff1-d974dbd67399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069625526","display_name":"Zeyu Zhao","orcid":"https://orcid.org/0000-0002-4070-2694"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zeyu Zhao","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.2825,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66335686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5922309160232544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4028926193714142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5922309160232544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4028926193714142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt61566.2024.10832327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f7d19ea6-2fb9-4dce-9ff1-d974dbd67399","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f7d19ea6-2fb9-4dce-9ff1-d974dbd67399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Zhao, Z & Bell, P 2025, Advancing CTC models for better speech alignment : A topological approach. in 2024 IEEE Spoken Language Technology Workshop (SLT). Proceedings of the IEEE Spoken Language Technology Workshop, Institute of Electrical and Electronics Engineers, Singapore, pp. 279-285, IEEE Spoken Language Technology Workshop 2024 , Macau, China, 2/12/24. https://doi.org/10.1109/SLT61566.2024.10832327","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f7d19ea6-2fb9-4dce-9ff1-d974dbd67399","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/472967606/AdvancingCTCModelsForBetterSpeechAlignment_accepted_vers_con_contrib_.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Zhao, Z & Bell, P 2025, Advancing CTC models for better speech alignment : A topological approach. in 2024 IEEE Spoken Language Technology Workshop (SLT). Proceedings of the IEEE Spoken Language Technology Workshop, Institute of Electrical and Electronics Engineers, Singapore, pp. 279-285, IEEE Spoken Language Technology Workshop 2024 , Macau, China, 2/12/24. https://doi.org/10.1109/SLT61566.2024.10832327","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f7d19ea6-2fb9-4dce-9ff1-d974dbd67399","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f7d19ea6-2fb9-4dce-9ff1-d974dbd67399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Zhao, Z & Bell, P 2025, Advancing CTC models for better speech alignment : A topological approach. in 2024 IEEE Spoken Language Technology Workshop (SLT). Proceedings of the IEEE Spoken Language Technology Workshop, Institute of Electrical and Electronics Engineers, Singapore, pp. 279-285, IEEE Spoken Language Technology Workshop 2024 , Macau, China, 2/12/24. https://doi.org/10.1109/SLT61566.2024.10832327","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1895481600","https://openalex.org/W2122364000","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2132991150","https://openalex.org/W2747874407","https://openalex.org/W2963211739","https://openalex.org/W3036601975","https://openalex.org/W3167895882","https://openalex.org/W3202184514","https://openalex.org/W4224925075","https://openalex.org/W4225272763","https://openalex.org/W4225741214","https://openalex.org/W4287647128","https://openalex.org/W4295312788","https://openalex.org/W4319862408","https://openalex.org/W4372260023","https://openalex.org/W4385822403","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6766978945","https://openalex.org/W6780218876","https://openalex.org/W6783314596","https://openalex.org/W6796656850","https://openalex.org/W6859267583"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"systems":[4],"often":[5],"face":[6],"challenges":[7],"in":[8,22,86,99,106],"alignment":[9,47,69,84,101],"quality,":[10],"particularly":[11],"with":[12],"the":[13,31,39,64,73,78,93],"Connectionist":[14],"Temporal":[15],"Classification":[16],"(CTC)":[17],"approach,":[18],"which":[19],"frequently":[20],"results":[21],"a":[23],"high":[24],"number":[25],"of":[26,41,96],"blank":[27],"frames,":[28],"known":[29],"as":[30],"\u201cpeaky\u201d":[32],"issue.":[33,75],"In":[34],"this":[35],"study,":[36],"we":[37],"explore":[38],"impact":[40],"modifying":[42],"ASR":[43,107],"model":[44],"topologies":[45],"on":[46],"quality":[48,70,85],"without":[49],"compromising":[50],"Word":[51],"Error":[52],"Rate":[53],"(WER)":[54],"performance.":[55],"Our":[56],"findings":[57],"demonstrate":[58],"that":[59],"introducing":[60],"additional":[61],"states":[62],"to":[63],"CTC":[65],"topology":[66,97],"significantly":[67],"improves":[68],"and":[71,103],"mitigates":[72],"peaky":[74],"Conversely,":[76],"increasing":[77],"minimum":[79],"traversal":[80],"frame":[81],"can":[82],"degrade":[83],"our":[87],"specific":[88],"settings.":[89],"These":[90],"insights":[91],"emphasise":[92],"critical":[94],"importance":[95],"design":[98],"balancing":[100],"accuracy":[102],"recognition":[104],"performance":[105],"systems.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}