{"id":"https://openalex.org/W4312661859","doi":"https://doi.org/10.1007/978-3-031-22321-1_16","title":"TransFusion: Transcribing Speech with\u00a0Multinomial Diffusion","display_name":"TransFusion: Transcribing Speech with\u00a0Multinomial Diffusion","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312661859","doi":"https://doi.org/10.1007/978-3-031-22321-1_16"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-22321-1_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-22321-1_16","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5085677838","display_name":"Matthew Baas","orcid":"https://orcid.org/0000-0003-3001-6292"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Matthew Baas","raw_affiliation_strings":["MediaLab, Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"],"raw_orcid":"https://orcid.org/0000-0003-3001-6292","affiliations":[{"raw_affiliation_string":"MediaLab, Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039211008","display_name":"Kevin Eloff","orcid":"https://orcid.org/0000-0003-1355-8743"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Kevin Eloff","raw_affiliation_strings":["MediaLab, Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"],"raw_orcid":"https://orcid.org/0000-0003-1355-8743","affiliations":[{"raw_affiliation_string":"MediaLab, Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["MediaLab, Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"],"raw_orcid":"https://orcid.org/0000-0003-2980-3475","affiliations":[{"raw_affiliation_string":"MediaLab, Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085677838"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.6847,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7443957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976999759674072,"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":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.7114739418029785},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6353094577789307},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5558567047119141},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5308117866516113},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5042327642440796},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.48603612184524536},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4823191165924072},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.46716225147247314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3728269338607788},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22404533624649048},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22294968366622925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7114739418029785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6353094577789307},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5558567047119141},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5308117866516113},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5042327642440796},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.48603612184524536},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4823191165924072},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46716225147247314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3728269338607788},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22404533624649048},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22294968366622925},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-22321-1_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-22321-1_16","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2769205094","https://openalex.org/W2995181338","https://openalex.org/W3026041220","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212516020","https://openalex.org/W4226033575","https://openalex.org/W4312497550","https://openalex.org/W6631455383","https://openalex.org/W6739901393","https://openalex.org/W6828894009"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W2375873920","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W2542937328","https://openalex.org/W2146114872","https://openalex.org/W4251141768","https://openalex.org/W4360952157"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
