{"id":"https://openalex.org/W2973143291","doi":"https://doi.org/10.21437/interspeech.2019-2623","title":"Untranscribed Web Audio for Low Resource Speech Recognition","display_name":"Untranscribed Web Audio for Low Resource Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973143291","doi":"https://doi.org/10.21437/interspeech.2019-2623","mag":"2973143291"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2623","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/99436264/Untranscribed_web_audio_CARMANTINI_DoA170619_AFV.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066016980","display_name":"Andrea Carmantini","orcid":"https://orcid.org/0000-0001-9016-5092"},"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":"Andrea Carmantini","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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, Edinburgh EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"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":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, 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":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"230"},"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.853402853012085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6692010164260864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5157299637794495},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.480308473110199},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45114442706108093},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42381197214126587},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41531866788864136},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2974667549133301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853402853012085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6692010164260864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157299637794495},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.480308473110199},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45114442706108093},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42381197214126587},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41531866788864136},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2974667549133301},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2019-2623","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/ebf4c0e7-58aa-41d3-a403-d465be4792c9","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ebf4c0e7-58aa-41d3-a403-d465be4792c9","pdf_url":"https://www.research.ed.ac.uk/files/99436264/Untranscribed_web_audio_CARMANTINI_DoA170619_AFV.pdf","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Carmantini, A, Bell, P & Renals, S 2019, Untranscribed web audio for low resource speech recognition. in Proceedings Interspeech 2019. International Speech Communication Association, pp. 226-230, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-2623","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/ebf4c0e7-58aa-41d3-a403-d465be4792c9","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/ebf4c0e7-58aa-41d3-a403-d465be4792c9","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Carmantini, A, Bell, P & Renals, S 2019, Untranscribed web audio for low resource speech recognition. in Proceedings Interspeech 2019. International Speech Communication Association, pp. 226-230, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-2623","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/ebf4c0e7-58aa-41d3-a403-d465be4792c9","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ebf4c0e7-58aa-41d3-a403-d465be4792c9","pdf_url":"https://www.research.ed.ac.uk/files/99436264/Untranscribed_web_audio_CARMANTINI_DoA170619_AFV.pdf","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Carmantini, A, Bell, P & Renals, S 2019, Untranscribed web audio for low resource speech recognition. in Proceedings Interspeech 2019. International Speech Communication Association, pp. 226-230, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-2623","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2973143291.pdf","grobid_xml":"https://content.openalex.org/works/W2973143291.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W1970890968","https://openalex.org/W1975113979","https://openalex.org/W1978963168","https://openalex.org/W2013598660","https://openalex.org/W2039716246","https://openalex.org/W2079623482","https://openalex.org/W2110073835","https://openalex.org/W2124558353","https://openalex.org/W2125107268","https://openalex.org/W2132991150","https://openalex.org/W2140914930","https://openalex.org/W2147152002","https://openalex.org/W2150769028","https://openalex.org/W2171761326","https://openalex.org/W2213952365","https://openalex.org/W2292656914","https://openalex.org/W2399742709","https://openalex.org/W2514741789","https://openalex.org/W2748146162","https://openalex.org/W2786459654","https://openalex.org/W2802248956","https://openalex.org/W2888867175","https://openalex.org/W2888908158","https://openalex.org/W2889162046","https://openalex.org/W2890964092","https://openalex.org/W2911629330","https://openalex.org/W4236080679"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W4383605217","https://openalex.org/W2533508831","https://openalex.org/W48790062","https://openalex.org/W2742699532","https://openalex.org/W4281389974","https://openalex.org/W1911859126","https://openalex.org/W2158598479","https://openalex.org/W2325482719"],"abstract_inverted_index":{"Speech":[0],"recognition":[1],"models":[2,68],"are":[3],"highly":[4],"susceptible":[5],"to":[6,28,53,59,87,92,102],"mismatch":[7,71],"in":[8,74],"the":[9,15,18,79,89,98,108,117],"acoustic":[10],"and":[11,17,69,129],"language":[12],"domains":[13],"between":[14],"training":[16],"evaluation":[19],"data.":[20],"For":[21],"low":[22],"resource":[23],"languages,":[24],"it":[25],"is":[26],"difficult":[27],"obtain":[29],"transcribed":[30],"speech":[31],"for":[32,62,78,126],"target":[33],"domains,":[34],"while":[35],"untranscribed":[36,54],"data":[37,55,106],"can":[38,72],"be":[39,60],"collected":[40],"with":[41,104],"minimal":[42],"effort.":[43],"Recently,":[44],"a":[45,85],"method":[46,86,115],"applying":[47],"lattice-free":[48],"maximum":[49],"mutual":[50],"information":[51],"(LF-MMI)":[52],"has":[56],"been":[57],"found":[58],"effective":[61],"semi-supervised":[63,80,114],"training.":[64],"However,":[65],"weaker":[66],"initial":[67],"domain":[70],"result":[73],"high":[75],"deletion":[76],"rates":[77],"model.":[81],"Therefore,":[82],"we":[83],"propose":[84],"force":[88],"base":[90],"model":[91],"overgenerate":[93],"possible":[94],"transcriptions,":[95],"relying":[96],"on":[97],"ability":[99],"of":[100],"LF-MMI":[101],"deal":[103],"uncertainty.<br/><br/>On":[105],"from":[107],"IARPA":[109],"MATERIAL":[110],"programme,":[111],"our":[112],"new":[113],"outperforms":[116],"standard":[118],"semisupervised":[119],"method,":[120],"yielding":[121],"significant":[122],"gains":[123],"when":[124],"adapting":[125],"mismatched":[127],"bandwidth":[128],"domain.<br/>":[130]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}