{"id":"https://openalex.org/W2940222629","doi":"https://doi.org/10.1109/icassp.2019.8682826","title":"Improving Children Speech Recognition through Feature Learning from Raw Speech Signal","display_name":"Improving Children Speech Recognition through Feature Learning from Raw Speech Signal","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940222629","doi":"https://doi.org/10.1109/icassp.2019.8682826","mag":"2940222629"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/264111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008235303","display_name":"S. Pavankumar Dubagunta","orcid":"https://orcid.org/0000-0002-4307-8604"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"S. Pavankumar Dubagunta","raw_affiliation_strings":["\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064475436","display_name":"Selen Hande Kabil","orcid":"https://orcid.org/0000-0002-2588-4047"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Selen Hande Kabil","raw_affiliation_strings":["\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4213,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.86749283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5736","last_page":"5740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9925000071525574,"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/speech-recognition","display_name":"Speech recognition","score":0.81522536277771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7344458699226379},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7125776410102844},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.561206579208374},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5171012878417969},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5044819116592407},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5034684538841248},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4954572916030884},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.482343852519989},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48149263858795166},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.47810620069503784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39422690868377686},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35412001609802246}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.81522536277771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344458699226379},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7125776410102844},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.561206579208374},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5171012878417969},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5044819116592407},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5034684538841248},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4954572916030884},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.482343852519989},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48149263858795166},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.47810620069503784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39422690868377686},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35412001609802246},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:264111","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/264111","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/264111","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:264111","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/264111","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/264111","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W88545716","https://openalex.org/W166258945","https://openalex.org/W1524333225","https://openalex.org/W1540779870","https://openalex.org/W1994888226","https://openalex.org/W2035781796","https://openalex.org/W2070696251","https://openalex.org/W2130722890","https://openalex.org/W2295983515","https://openalex.org/W2398826216","https://openalex.org/W2401869809","https://openalex.org/W2402172738","https://openalex.org/W2511419867","https://openalex.org/W2566781703","https://openalex.org/W2770454110","https://openalex.org/W2776923314","https://openalex.org/W2887376701","https://openalex.org/W2887949187","https://openalex.org/W2963175699","https://openalex.org/W6631362777","https://openalex.org/W6678409544","https://openalex.org/W6679230416","https://openalex.org/W6697215464","https://openalex.org/W6712560600","https://openalex.org/W6713197546","https://openalex.org/W6753678270"],"related_works":["https://openalex.org/W2049648127","https://openalex.org/W193702574","https://openalex.org/W2096476291","https://openalex.org/W109432504","https://openalex.org/W1523214805","https://openalex.org/W4294771049","https://openalex.org/W2559040841","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Children":[0],"speech":[1,19,52,78,90],"recognition":[2,91],"based":[3],"on":[4,83],"short-term":[5,47],"spectral":[6],"features":[7,49],"is":[8,16,25],"a":[9],"challenging":[10],"task.":[11],"One":[12],"of":[13],"the":[14,66,76],"reasons":[15],"that":[17,24,63,88],"children":[18,33,89],"has":[20],"high":[21],"fundamental":[22],"frequency":[23,29],"comparable":[26],"to":[27],"formant":[28],"values.":[30],"Furthermore,":[31],"as":[32],"grow,":[34],"their":[35],"vocal":[36],"apparatus":[37],"also":[38],"undergoes":[39],"changes.":[40],"This":[41],"presents":[42],"difficulties":[43],"in":[44,71],"extracting":[45],"standard":[46],"spectral-based":[48],"reliably":[50],"for":[51],"recognition.":[53],"In":[54],"recent":[55],"years,":[56],"novel":[57],"acoustic":[58,97],"modeling":[59,98],"methods":[60],"have":[61],"emerged":[62],"learn":[64],"both":[65],"feature":[67],"and":[68],"phone":[69],"classifier":[70],"an":[72,81],"end-to-end":[73,96],"manner":[74],"from":[75],"raw":[77],"signal.":[79],"Through":[80],"investigation":[82],"PF-STAR":[84],"corpus":[85],"we":[86],"show":[87],"can":[92],"be":[93],"improved":[94],"using":[95],"methods.":[99]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}