{"id":"https://openalex.org/W2998632136","doi":"https://doi.org/10.1109/hsi47298.2019.8942638","title":"Combining Data Augmentations for CNN-Based Voice Command Recognition","display_name":"Combining Data Augmentations for CNN-Based Voice Command Recognition","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2998632136","doi":"https://doi.org/10.1109/hsi47298.2019.8942638","mag":"2998632136"},"language":"en","primary_location":{"id":"doi:10.1109/hsi47298.2019.8942638","doi":"https://doi.org/10.1109/hsi47298.2019.8942638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hsi47298.2019.8942638","pdf_url":null,"source":{"id":"https://openalex.org/S4306418059","display_name":"Conference on Human System Interactions","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 12th International Conference on Human System Interaction (HSI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5079917233","display_name":"Arian Azarang","orcid":"https://orcid.org/0000-0001-8520-8457","observed_orcids":["https://orcid.org/0000-0001-8520-8457"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arian Azarang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Hansen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076371436","display_name":"Nasser Kehtarnavaz","orcid":"https://orcid.org/0000-0001-5183-6359","observed_orcids":["https://orcid.org/0000-0001-5183-6359"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nasser Kehtarnavaz","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.6697,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7591662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9940999746322632,"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":0.9940999746322632,"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":0.005799999926239252,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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/voice-command-recognition","display_name":"voice command recognition","score":0.9700000286102295},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.9779999852180481},{"id":"https://openalex.org/keywords/speed-perturbation","display_name":"speed perturbation","score":0.9729999899864197},{"id":"https://openalex.org/keywords/room-impulse-response","display_name":"room impulse response","score":0.9639999866485596},{"id":"https://openalex.org/keywords/reverberation","display_name":"reverberation","score":0.9700000286102295},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9649999737739563},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.875},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.871999979019165},{"id":"https://openalex.org/keywords/acoustic-variability","display_name":"acoustic variability","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939599752426147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7428567409515381},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6852114200592041},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6489030122756958},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.6150264143943787},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5384658575057983},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.470790296792984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3338649868965149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3289526700973511},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14702945947647095},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0716848075389862},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hsi47298.2019.8942638","doi":"https://doi.org/10.1109/hsi47298.2019.8942638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hsi47298.2019.8942638","pdf_url":null,"source":{"id":"https://openalex.org/S4306418059","display_name":"Conference on Human System Interactions","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 12th International Conference on Human System Interaction (HSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1500987701","https://openalex.org/W1509793305","https://openalex.org/W1544986415","https://openalex.org/W2143742681","https://openalex.org/W2303635780","https://openalex.org/W2407080277","https://openalex.org/W2509065397","https://openalex.org/W2546885909","https://openalex.org/W2696967604","https://openalex.org/W2724968249","https://openalex.org/W2737108017","https://openalex.org/W2751926801","https://openalex.org/W2771304733","https://openalex.org/W2785451509","https://openalex.org/W2797583228","https://openalex.org/W2889018940","https://openalex.org/W2889385306","https://openalex.org/W3143835353"],"related_works":["https://openalex.org/W2938908509","https://openalex.org/W2773005317","https://openalex.org/W4327521002","https://openalex.org/W7143511157","https://openalex.org/W3109147806","https://openalex.org/W3017022801","https://openalex.org/W2964215376","https://openalex.org/W4225325562","https://openalex.org/W4405533178","https://openalex.org/W2407080277"],"abstract_inverted_index":{"This":[0],"paper":[1,77],"presents":[2],"combining":[3,108],"two":[4,70],"data":[5,110],"augmentation":[6,71,111,117],"methods":[7,72,112],"involving":[8],"speed":[9],"perturbation":[10,35],"and":[11],"room":[12],"impulse":[13,54],"response":[14,55],"reverberation":[15,56],"for":[16,30],"the":[17,21,92,100],"purpose":[18],"of":[19,24,47,68,84,95],"improving":[20],"generalization":[22],"capability":[23],"convolutional":[25],"neural":[26],"networks":[27],"when":[28,107],"used":[29],"voice":[31,37,58,85,103],"command":[32,38,59,104],"recognition.":[33],"Speed":[34],"generates":[36,57],"variations":[39,60],"caused":[40,61],"by":[41,50,62,78],"shorter":[42],"or":[43],"longer":[44],"time":[45],"durations":[46],"commands":[48],"spoken":[49],"different":[51],"speakers.":[52],"Room":[53],"reflected":[63],"sound":[64],"paths.":[65],"The":[66,87],"combination":[67],"these":[69,109],"is":[73],"presented":[74],"in":[75,102],"this":[76],"examining":[79],"a":[80],"public":[81],"domain":[82],"dataset":[83],"commands.":[86],"experimental":[88],"results":[89],"based":[90],"on":[91],"performance":[93],"metric":[94],"word":[96],"error":[97],"rate":[98],"indicate":[99],"improvement":[101],"recognition":[105],"rates":[106],"relative":[113],"to":[114],"using":[115],"each":[116],"method":[118],"individually.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2020-01-10T00:00:00"}