{"id":"https://openalex.org/W4385822403","doi":"https://doi.org/10.21437/interspeech.2023-2186","title":"Regarding Topology and Variant Frame Rates for Differentiable WFST-based End-to-End ASR","display_name":"Regarding Topology and Variant Frame Rates for Differentiable WFST-based End-to-End ASR","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822403","doi":"https://doi.org/10.21437/interspeech.2023-2186"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2186","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/files/370157283/Regarding_Topology_ZHAO_DOA17052023_AFV_CC_BY.pdf","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":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","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":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","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":0.4801,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68843131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4903","last_page":"4907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/network-topology","display_name":"Network topology","score":0.818938672542572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6249021887779236},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.6128659844398499},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5143986344337463},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5083550810813904},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4692041277885437},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.45769980549812317},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4445056617259979},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.4426473379135132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.357006698846817},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35097557306289673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34105032682418823},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25727492570877075},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24474412202835083},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13478359580039978},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07404723763465881}],"concepts":[{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.818938672542572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6249021887779236},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.6128659844398499},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5143986344337463},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5083550810813904},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4692041277885437},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.45769980549812317},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4445056617259979},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.4426473379135132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.357006698846817},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35097557306289673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34105032682418823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25727492570877075},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24474412202835083},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13478359580039978},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07404723763465881},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-2186","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/30537ecf-24f8-411d-a4d1-32f921853b24","is_oa":true,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2023/zhao23f_interspeech.html","pdf_url":"https://www.research.ed.ac.uk/files/370157283/Regarding_Topology_ZHAO_DOA17052023_AFV_CC_BY.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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 2023, Regarding Topology and Variant Frame Rates for Differentiable WFST-based End-to-End ASR. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 4903-4907, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-2186","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/30537ecf-24f8-411d-a4d1-32f921853b24","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/30537ecf-24f8-411d-a4d1-32f921853b24","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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 2023, Regarding Topology and Variant Frame Rates for Differentiable WFST-based End-to-End ASR. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 4903-4907, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-2186","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/30537ecf-24f8-411d-a4d1-32f921853b24","is_oa":true,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2023/zhao23f_interspeech.html","pdf_url":"https://www.research.ed.ac.uk/files/370157283/Regarding_Topology_ZHAO_DOA17052023_AFV_CC_BY.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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 2023, Regarding Topology and Variant Frame Rates for Differentiable WFST-based End-to-End ASR. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 4903-4907, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-2186","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822403.pdf","grobid_xml":"https://content.openalex.org/works/W4385822403.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W1895481600","https://openalex.org/W1989226853","https://openalex.org/W2105594594","https://openalex.org/W2132991150","https://openalex.org/W2142416747","https://openalex.org/W2514741789","https://openalex.org/W2748816379","https://openalex.org/W2808939837","https://openalex.org/W2889282842","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963211739","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3163793923","https://openalex.org/W3202184514","https://openalex.org/W3209059054","https://openalex.org/W4212827537","https://openalex.org/W4224925075","https://openalex.org/W4252331534","https://openalex.org/W4253573210","https://openalex.org/W4287647128","https://openalex.org/W4295312788","https://openalex.org/W4303493483","https://openalex.org/W4304764782","https://openalex.org/W4319862408","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W170547082","https://openalex.org/W2136735429","https://openalex.org/W2587876411","https://openalex.org/W2358332176","https://openalex.org/W4229950834","https://openalex.org/W4205841273","https://openalex.org/W4301044568","https://openalex.org/W4205525690","https://openalex.org/W1587123803","https://openalex.org/W2128075414"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"Automatic":[2],"Speech":[3],"Recognition":[4],"(ASR)":[5],"has":[6,36],"gained":[7],"popularity":[8],"in":[9,33,48,130],"recent":[10],"years,":[11],"with":[12],"most":[13],"research":[14],"focusing":[15],"on":[16,53,86],"designing":[17],"novel":[18],"neural":[19],"network":[20],"architectures,":[21],"speech":[22],"rep":[23],"resentations,":[24],"and":[25,61,74,90,103],"loss":[26],"functions.":[27],"However,":[28],"the":[29,54,65,75,105,121,131],"importance":[30],"of":[31,44,67,77,123,133],"topology":[32,45,112],"E2E":[34,134],"ASR":[35,135],"been":[37],"largely":[38],"neglected.":[39],"There":[40],"are":[41],"many":[42],"aspects":[43],"to":[46],"consider;":[47],"this":[49],"paper,":[50],"we":[51],"focus":[52],"relationship":[55],"between":[56],"topologies\u2019":[57],"minimum":[58],"traversal":[59],"time":[60],"output":[62,72],"frame":[63,97],"rate,":[64],"number":[66],"distinct":[68],"states":[69],"for":[70],"each":[71],"unit,":[73],"flexibility":[76],"alignments":[78],"admitted.":[79],"We":[80],"ex":[81],"amine":[82],"several":[83],"different":[84,96],"topologies":[85,102],"two":[87],"datasets:":[88],"WSJ":[89],"Librispeech.":[91],"Our":[92,117],"experiments":[93],"reveal":[94],"that":[95,104,120],"rates":[98],"have":[99],"varying":[100],"optimal":[101],"commonly":[106],"used":[107],"Connectionist":[108],"Temporal":[109],"Classification":[110],"(CTC)":[111],"is":[113,126],"not":[114],"always":[115],"optimal.":[116],"findings":[118],"suggest":[119],"choice":[122],"topol":[124],"ogy":[125],"an":[127],"important":[128],"consideration":[129],"design":[132],"systems.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
