{"id":"https://openalex.org/W37822302","doi":"https://doi.org/10.21437/eurospeech.2001-431","title":"Improving automatic speech recognition using tangent distance","display_name":"Improving automatic speech recognition using tangent distance","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W37822302","doi":"https://doi.org/10.21437/eurospeech.2001-431","mag":"37822302"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-431","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.rwth-aachen.de/record/111403","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018646392","display_name":"Wolfgang Macherey","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"W. Macherey","raw_affiliation_strings":["[Rwth Aachen University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Rwth Aachen University]","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066294527","display_name":"Daniel Keysers","orcid":"https://orcid.org/0000-0001-8765-475X"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Keysers","raw_affiliation_strings":["Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004679893","display_name":"J. Dahmen","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. Dahmen","raw_affiliation_strings":["Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7276,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74184141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1825","last_page":"1828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9840999841690063,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.984000027179718,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6316772699356079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.603300929069519},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5931580066680908},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.586214542388916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5805496573448181},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4764550030231476},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4597930908203125},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42657142877578735},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4255087375640869},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4144183099269867},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31470176577568054},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29745063185691833}],"concepts":[{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6316772699356079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.603300929069519},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5931580066680908},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.586214542388916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805496573448181},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4764550030231476},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4597930908203125},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42657142877578735},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4255087375640869},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4144183099269867},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31470176577568054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29745063185691833},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/eurospeech.2001-431","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:111403","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/111403","pdf_url":"http://publications.rwth-aachen.de/record/111403","source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings / Eurospeech 2001, Scandinavia, 7th European Conference on Speech Communication and Technology, September 3 - 7, 2001, Aalborg Congress and Culture Centre, Aalborg, Denmark / organised by Center for Personkommunikation, Aalborg University, Denmark / Paul Dalsgaard. - Vol. 3.<br/>7. European Conference on Speech Communication and Technology, Aalborg, Denmark, 2001-09-03 - 2001-09-07","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.9117","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.9117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.keysers.net/daniel/files/EUROSPEECH2001Macherey.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.4710","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.4710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/~keysers/EUROSPEECH2001Macherey.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.2473","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.2473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/113/MachereyWolfgangKeysersDanielDahmenJ%7Bo%7DrgNeyHermann--ImprovingAutomaticSpeechRecognitionUsingTangentDistance--2001.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.4886","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.4886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/PostScript/InterneArbeiten/Paper_2001/MachereyW_ASRTangentDist_EUROSPEECH_2001.ps","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:publications.rwth-aachen.de:111403","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/111403","pdf_url":"http://publications.rwth-aachen.de/record/111403","source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings / Eurospeech 2001, Scandinavia, 7th European Conference on Speech Communication and Technology, September 3 - 7, 2001, Aalborg Congress and Culture Centre, Aalborg, Denmark / organised by Center for Personkommunikation, Aalborg University, Denmark / Paul Dalsgaard. - Vol. 3.<br/>7. European Conference on Speech Communication and Technology, Aalborg, Denmark, 2001-09-03 - 2001-09-07","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W37822302.pdf","grobid_xml":"https://content.openalex.org/works/W37822302.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W92824239","https://openalex.org/W1481810092","https://openalex.org/W1581041165","https://openalex.org/W1590403649","https://openalex.org/W2071111253","https://openalex.org/W2101430057","https://openalex.org/W2111494971","https://openalex.org/W2135346934","https://openalex.org/W2137291015","https://openalex.org/W2294460823","https://openalex.org/W4249522262","https://openalex.org/W4301031934"],"related_works":["https://openalex.org/W1620410898","https://openalex.org/W3026007073","https://openalex.org/W4294624138","https://openalex.org/W4388322466","https://openalex.org/W4295806272","https://openalex.org/W4226324615","https://openalex.org/W2189435847","https://openalex.org/W4300349471","https://openalex.org/W2100099236","https://openalex.org/W1575585820"],"abstract_inverted_index":{"In":[0,94],"this":[1,85,95],"paper":[2,96],"we":[3,97],"present":[4],"a":[5,39,42,63,119,136,142,147],"new":[6],"approach":[7,86,145],"to":[8,49],"variance":[9],"modelling":[10],"in":[11,41,75,90,139],"automatic":[12],"speech":[13],"recognition":[14],"(ASR)":[15],"that":[16,77],"is":[17,78,116],"based":[18,107],"on":[19,108,124],"tangent":[20],"distance":[21,58,70],"(TD).":[22],"Using":[23],"TD,":[24],"classifiers":[25,55],"can":[26,101],"be":[27,102],"made":[28],"invariant":[29,79],"w.r.t.":[30,80],"small":[31],"transformations":[32,37],"of":[33,150],"the":[34,57,68,81,125],"data.":[35],"Such":[36],"generate":[38],"manifold":[40],"high":[43],"dimensional":[44],"feature":[45],"space":[46],"when":[47],"applied":[48,89],"an":[50,60],"observation":[51,61],"vector.":[52],"While":[53],"conventional":[54,143],"determine":[56],"between":[59,71],"and":[62],"prototype":[64],"vector,":[65],"TD":[66,100],"approximates":[67],"minimum":[69],"their":[72],"manifolds,":[73],"resulting":[74],"classification":[76],"underlying":[82],"transformation.":[83],"Recently,":[84],"was":[87],"successfully":[88],"image":[91],"object":[92],"recognition.":[93],"describe":[98],"how":[99],"incorporated":[103],"into":[104,118],"ASR":[105],"systems":[106],"Gaussian":[109],"mixture":[110],"densities":[111],"(GMD).":[112],"The":[113],"proposed":[114],"method":[115],"embedded":[117],"probabilistic":[120],"framework.":[121],"Experiments":[122],"performed":[123],"SieTill":[126],"corpus":[127],"for":[128],"telephone":[129],"line":[130],"recorded":[131],"German":[132],"digit":[133],"strings":[134],"show":[135],"significant":[137],"improvement":[138],"comparison":[140],"with":[141],"GMD":[144],"using":[146],"comparable":[148],"amount":[149],"model":[151],"parameters.":[152],"1.":[153]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}