{"id":"https://openalex.org/W2901697556","doi":"https://doi.org/10.21437/iberspeech.2018-57","title":"Intelligent Voice ASR system for Iberspeech 2018 Speech to Text Transcription Challenge","display_name":"Intelligent Voice ASR system for Iberspeech 2018 Speech to Text Transcription Challenge","publication_year":2018,"publication_date":"2018-11-19","ids":{"openalex":"https://openalex.org/W2901697556","doi":"https://doi.org/10.21437/iberspeech.2018-57","mag":"2901697556"},"language":"en","primary_location":{"id":"doi:10.21437/iberspeech.2018-57","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2018-57","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2018","raw_type":"proceedings-article"},"type":"preprint","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/A5076271433","display_name":"Naz\u0131m Dugan","orcid":"https://orcid.org/0000-0002-3620-6225"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nazim Dugan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044554092","display_name":"Cornelius Glackin","orcid":"https://orcid.org/0000-0001-5114-6403"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cornelius Glackin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054175637","display_name":"G\u00e9rard Chollet","orcid":"https://orcid.org/0000-0003-4245-146X"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4387153010","display_name":"T\u00e9l\u00e9com SudParis","ror":"https://ror.org/05xvk4r52","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00e9rard Chollet","raw_affiliation_strings":["ARMEDIA-SAMOVAR - ARMEDIA (TELECOM Sudparis\r\n 9 rue Charles Fourier\r\n 91011 EVRY - France)","TSP - EPH - D\u00e9partement Electronique et Physique (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry Cedex - France)","IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)"],"affiliations":[{"raw_affiliation_string":"ARMEDIA-SAMOVAR - ARMEDIA (TELECOM Sudparis\r\n 9 rue Charles Fourier\r\n 91011 EVRY - France)","institution_ids":["https://openalex.org/I4387153010"]},{"raw_affiliation_string":"TSP - EPH - D\u00e9partement Electronique et Physique (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry Cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4387153010"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","institution_ids":["https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012466886","display_name":"Nigel Cannings","orcid":"https://orcid.org/0000-0002-5279-3968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nigel Cannings","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076271433"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5112,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75057717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9185000061988831,"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":0.8158257007598877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7712899446487427},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6539897918701172},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5730375647544861},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5499722957611084},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5304267406463623},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4753822386264801},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.44222739338874817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44043800234794617},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.43110162019729614},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.410259872674942},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3522801399230957},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.12614458799362183},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08832171559333801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158257007598877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7712899446487427},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6539897918701172},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5730375647544861},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5499722957611084},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5304267406463623},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4753822386264801},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.44222739338874817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44043800234794617},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.43110162019729614},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.410259872674942},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3522801399230957},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.12614458799362183},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08832171559333801},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/iberspeech.2018-57","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2018-57","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02288554v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-02288554","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IberSPEECH 2018, Nov 2018, Barcelone, Spain. pp.272-276, ⟨10.21437/IberSPEECH.2018-57⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W1656519308","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W4401571341"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,7,11,16,39,89,98,109,118,136],"system":[4,121],"developed":[5],"by":[6,92,129],"Empathic":[8],"team":[9],"for":[10,47],"open":[12],"set":[13],"condition":[14],"of":[15,79,88,112,143,146],"Iberspeech":[17],"2018":[18],"Speech":[19],"to":[20,116],"Text":[21],"Transcription":[22],"Challenge.":[23],"A":[24],"DNN-HMM":[25],"hybrid":[26],"acoustic":[27],"model":[28],"is":[29,81,106],"developed,":[30],"with":[31,108,122],"MFCC's":[32],"and":[33,49,58,85],"iVectors":[34],"as":[35],"input":[36],"features,":[37],"using":[38,54,61,131],"Kaldi":[40],"framework.":[41],"The":[42,103],"provided":[43,90],"ground":[44],"truth":[45],"transcriptions":[46],"training":[48,113,138],"development":[50],"are":[51],"cleaned":[52],"up":[53],"customized":[55],"clean-up":[56],"scripts":[57],"then":[59],"realigned":[60],"a":[62,73,94,123,132,141],"two-step":[63],"alignment":[64],"procedure":[65],"which":[66],"uses":[67],"word":[68],"lattice":[69],"results":[70],"coming":[71],"from":[72,83],"previous":[74,119],"ASR":[75,120],"system.":[76],"261":[77],"hours":[78,111,145],"data":[80,105,114,127],"selected":[82,104],"train":[84,117],"dev1":[86],"subsections":[87],"data,":[91,139],"applying":[93],"selection":[95],"criterion":[96],"on":[97,135],"utterance":[99],"level":[100],"scoring":[101],"results.":[102],"merged":[107],"91":[110],"used":[115],"factor":[124],"3":[125],"times":[126],"augmentation":[128],"reverberation":[130],"noise":[133],"corpus":[134],"total":[137,142],"resulting":[140],"1057":[144],"final":[147],"\u2026":[148]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}