{"id":"https://openalex.org/W2512885752","doi":"https://doi.org/10.5220/0005955500650071","title":"Study on the Use and Adaptation of Bottleneck Features for Robust Speech Recognition of Nonlinearly Distorted Speech","display_name":"Study on the Use and Adaptation of Bottleneck Features for Robust Speech Recognition of Nonlinearly Distorted Speech","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2512885752","doi":"https://doi.org/10.5220/0005955500650071","mag":"2512885752"},"language":"en","primary_location":{"id":"doi:10.5220/0005955500650071","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005955500650071","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Joint Conference on e-Business and Telecommunications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005955500650071","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102731459","display_name":"Ji\u0159\u00ed M\u00e1lek","orcid":"https://orcid.org/0000-0002-5864-0196"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Jiri Malek","raw_affiliation_strings":["Technical University of Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007129369","display_name":"Petr \u010cerva","orcid":"https://orcid.org/0000-0003-0767-0106"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Cerva","raw_affiliation_strings":["Technical University of Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075473112","display_name":"Ladislav \u0160eps","orcid":null},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ladislav Seps","raw_affiliation_strings":["Technical University of Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033391650","display_name":"Jan Nouza","orcid":"https://orcid.org/0000-0003-3960-3194"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Nouza","raw_affiliation_strings":["Technical University of Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102731459"],"corresponding_institution_ids":["https://openalex.org/I147009085"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05113706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9966999888420105,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8130692839622498},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7566226720809937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7462171912193298},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6203175187110901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35023581981658936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34761887788772583},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08977848291397095}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8130692839622498},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7566226720809937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462171912193298},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6203175187110901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35023581981658936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34761887788772583},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08977848291397095},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0005955500650071","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005955500650071","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Joint Conference on e-Business and Telecommunications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0005955500650071","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005955500650071","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Joint Conference on e-Business and Telecommunications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W3192589309"],"abstract_inverted_index":{"This":[0],"paper":[1,52],"focuses":[2],"on":[3,22],"the":[4,54,65,73,122,131,147],"robust":[5],"recognition":[6,49],"of":[7,25,56,60,92,112,117,133],"nonlinearly":[8],"distorted":[9],"speech.":[10],"We":[11],"have":[12],"reported":[13],"(Seps":[14],"et":[15],"al.,\r\n\r\n2014)":[16],"that":[17,121],"hybrid":[18],"acoustic":[19,69,95],"models":[20,96,129],"based":[21,94],"a":[23],"combination":[24],"Hidden":[26],"Markov":[27],"Models":[28],"and":[29,97,136],"Deep":[30],"Neural":[31],"Networks\r\n\r\n(HMM-DNNs)":[32],"are":[33,77],"better":[34],"suited":[35],"to":[36,67,79],"this":[37,51],"task":[38],"than":[39],"conventional":[40],"HMMs":[41],"utilizing":[42],"Gaussian":[43],"Mixture":[44],"Models\r\n\r\n(HMM-GMMs).":[45],"To":[46],"further":[47],"improve":[48],"accuracy,":[50],"investigates":[53],"possibility":[55],"combining\r\n\r\nthe":[57],"modeling":[58],"power":[59],"deep":[61,74],"neural":[62,75],"networks":[63,76],"with":[64],"adaptation":[66],"given":[68],"conditions.":[70],"For":[71],"this\r\n\r\npurpose,":[72],"utilized":[78],"produce":[80],"bottleneck":[81],"coefficients":[82],"/":[83],"features":[84,119],"(BNC).":[85],"The":[86],"BNCs\r\n\r\nare":[87],"subsequently":[88],"used":[89],"for":[90,109,141],"training":[91],"HMM-GMM":[93],"then":[98],"adapted":[99,123],"using":[100],"Constrained\r\n\r\nMaximum":[101],"Likelihood":[102],"Linear":[103],"Regression":[104],"(CMLLR).":[105],"Our":[106],"results":[107],"obtained":[108],"three":[110,115],"types":[111,116],"nonlinear":[113,144],"distortions\r\n\r\nand":[114],"input":[118],"show":[120],"BNC-based":[124],"system":[125],"(a)":[126],"outperforms":[127],"HMM-DNN\r\n\r\nacoustic":[128],"in":[130,146],"case":[132],"strong":[134],"compression":[135],"(b)":[137],"yields":[138],"comparable":[139],"performance":[140],"speech":[142],"affected\r\n\r\nby":[143],"amplification":[145],"analog":[148],"domain.":[149]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
