{"id":"https://openalex.org/W7155488311","doi":"https://doi.org/10.1007/s13042-026-03084-7","title":"Enhancing continuous speech recognition with CapsNet and WaveRNN: a transfer learning approach","display_name":"Enhancing continuous speech recognition with CapsNet and WaveRNN: a transfer learning approach","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7155488311","doi":"https://doi.org/10.1007/s13042-026-03084-7"},"language":"en","primary_location":{"id":"doi:10.1007/s13042-026-03084-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-026-03084-7","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"},"type":"article","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/A5126802853","display_name":"Emna Bouhajeb","orcid":null},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210131288","display_name":"National Engineering School of Tunis","ror":"https://ror.org/03b1zjt31","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210131288","https://openalex.org/I63596082"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Emna Bouhajeb","raw_affiliation_strings":["Facult\u00e9 des Sciences de Tunis, Universit\u00e9 de Tunis El Manar, Campus Universitaire, El Manar, 2092, Tunis, Tunisia","LR-SITI, \u00c9cole Nationale d\u2019Ing\u00e9nieurs de Tunis, Universit\u00e9 de Tunis El Manar, BP 37, Le Belv\u00e9d\u00e8re, 1002, Tunis, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facult\u00e9 des Sciences de Tunis, Universit\u00e9 de Tunis El Manar, Campus Universitaire, El Manar, 2092, Tunis, Tunisia","institution_ids":["https://openalex.org/I108714496","https://openalex.org/I63596082"]},{"raw_affiliation_string":"LR-SITI, \u00c9cole Nationale d\u2019Ing\u00e9nieurs de Tunis, Universit\u00e9 de Tunis El Manar, BP 37, Le Belv\u00e9d\u00e8re, 1002, Tunis, Tunisia","institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210131288","https://openalex.org/I63596082"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050520709","display_name":"Chiraz Jlassi","orcid":null},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210131288","display_name":"National Engineering School of Tunis","ror":"https://ror.org/03b1zjt31","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210131288","https://openalex.org/I63596082"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Chiraz Jlassi","raw_affiliation_strings":["LR-SITI, \u00c9cole Nationale d\u2019Ing\u00e9nieurs de Tunis, Universit\u00e9 de Tunis El Manar, BP 37, Le Belv\u00e9d\u00e8re, 1002, Tunis, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LR-SITI, \u00c9cole Nationale d\u2019Ing\u00e9nieurs de Tunis, Universit\u00e9 de Tunis El Manar, BP 37, Le Belv\u00e9d\u00e8re, 1002, Tunis, Tunisia","institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210131288","https://openalex.org/I63596082"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057921627","display_name":"Najet Arous","orcid":null},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210131288","display_name":"National Engineering School of Tunis","ror":"https://ror.org/03b1zjt31","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210131288","https://openalex.org/I63596082"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Najet Arous","raw_affiliation_strings":["LR-SITI, \u00c9cole Nationale d\u2019Ing\u00e9nieurs de Tunis, Universit\u00e9 de Tunis El Manar, BP 37, Le Belv\u00e9d\u00e8re, 1002, Tunis, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LR-SITI, \u00c9cole Nationale d\u2019Ing\u00e9nieurs de Tunis, Universit\u00e9 de Tunis El Manar, BP 37, Le Belv\u00e9d\u00e8re, 1002, Tunis, Tunisia","institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210131288","https://openalex.org/I63596082"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5126802853"],"corresponding_institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210131288","https://openalex.org/I63596082"],"apc_list":{"value":3590,"currency":"USD","value_usd":3590},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47554541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"6","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":0.9409999847412109,"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":0.9409999847412109,"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":0.013000000268220901,"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":0.007600000128149986,"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/timit","display_name":"TIMIT","score":0.6495000123977661},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6402000188827515},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.44190001487731934},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39800000190734863},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.3946000039577484},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.37619999051094055},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36640000343322754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319000005722046},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6495000123977661},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6402000188827515},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.616599977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5324000120162964},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.3946000039577484},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.34619998931884766},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13042-026-03084-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-026-03084-7","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1995875735","https://openalex.org/W2020100920","https://openalex.org/W2080028048","https://openalex.org/W2476470546","https://openalex.org/W2963341956","https://openalex.org/W2963691377","https://openalex.org/W2973049979","https://openalex.org/W3037164260","https://openalex.org/W3041133507","https://openalex.org/W3128989309","https://openalex.org/W3131922516","https://openalex.org/W3136420808","https://openalex.org/W3149695349","https://openalex.org/W3154173985","https://openalex.org/W3160551958","https://openalex.org/W3176409535","https://openalex.org/W3182465333","https://openalex.org/W3200318528","https://openalex.org/W3205854703","https://openalex.org/W3211278025","https://openalex.org/W4221140846","https://openalex.org/W4321374412","https://openalex.org/W4375868885","https://openalex.org/W4378419886","https://openalex.org/W4379193822","https://openalex.org/W4385497926","https://openalex.org/W4385822766","https://openalex.org/W4389265550","https://openalex.org/W4393942507","https://openalex.org/W4394611093","https://openalex.org/W4394816493","https://openalex.org/W4396735698","https://openalex.org/W4401042959","https://openalex.org/W4401070302","https://openalex.org/W4402111558","https://openalex.org/W4402571630","https://openalex.org/W4402629542","https://openalex.org/W4409375459","https://openalex.org/W4410431605","https://openalex.org/W4413206048","https://openalex.org/W4414374254"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-04-25T00:00:00"}
