{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:45:29Z","timestamp":1782992729982,"version":"3.54.5"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16200-4","type":"journal-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T02:02:02Z","timestamp":1690855322000},"page":"17601-17628","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["A comprehensive experimental study for analyzing the effects of data augmentation techniques on voice classification"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3327-2822","authenticated-orcid":false,"given":"Halit","family":"Bak\u0131r","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ay\u015fe Nur","family":"\u00c7ay\u0131r","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tu\u011fba Selcen","family":"Navruz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,1]]},"reference":[{"key":"16200_CR1","doi-asserted-by":"publisher","first-page":"109209","DOI":"10.1016\/j.apacoust.2023.109209","volume":"203","author":"A Abeysinghe","year":"2023","unstructured":"Abeysinghe A, Tohmuang S, Davy JL, Fard M (2023) Data augmentation on convolutional neural networks to classify mechanical noise. Appl Acoust 203:109209","journal-title":"Appl Acoust"},{"issue":"3","key":"16200_CR2","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.3390\/app12031091","volume":"12","author":"MH Ali","year":"2022","unstructured":"Ali MH et al (2022) Harris hawks sparse auto-encoder networks for automatic speech recognition system. Appl Sci 12(3):1091","journal-title":"Appl Sci"},{"key":"16200_CR3","volume-title":"Some commonly used speech feature extraction algorithms","author":"SA Alim","year":"2018","unstructured":"Alim SA, Rashid NKA (2018) Some commonly used speech feature extraction algorithms. IntechOpen London, UK"},{"key":"16200_CR4","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-3-031-24468-1_11","volume-title":"Advances in artificial systems for medicine and education VI","author":"A Aswad","year":"2023","unstructured":"Aswad A, Alghannam E, Zhang Q (2023) Developing MFCC-CNN based voice recognition system with data augmentation and overfitting solving techniques. In: Advances in artificial systems for medicine and education VI. Springer, pp 115\u2013125"},{"key":"16200_CR5","unstructured":"Ate\u015f E (2019) Derin \u00f6\u011frenme ile sesli komut tan\u0131ma. ESOG\u00dc, Fen Bilimleri Enstit\u00fcs\u00fc"},{"issue":"1","key":"16200_CR6","first-page":"285","volume":"11","author":"M Bansal","year":"2020","unstructured":"Bansal M, Thivakaran DTK (2020) Analysis of speech recognition using convolutional neural network. J Eng Sci 11(1):285\u2013291","journal-title":"J Eng Sci"},{"key":"16200_CR7","doi-asserted-by":"publisher","first-page":"2048","DOI":"10.1016\/j.procs.2017.08.250","volume":"112","author":"V Boddapati","year":"2017","unstructured":"Boddapati V, Petef A, Rasmusson J, Lundberg L (2017) Classifying environmental sounds using image recognition networks. Proc Comput Sci 112:2048\u20132056","journal-title":"Proc Comput Sci"},{"key":"16200_CR8","volume-title":"Deep learning based voice command system","author":"AN \u00c7ay\u0131r","year":"2021","unstructured":"\u00c7ay\u0131r AN (2021) Deep learning based voice command system. Gazi University"},{"key":"16200_CR9","first-page":"1","volume-title":"2021 3rd international congress on human-computer interaction, optimization and robotic applications (HORA)","author":"AN \u00c7ay\u0131r","year":"2021","unstructured":"\u00c7ay\u0131r AN, Navruz TS (2021) Effect of dataset size on deep learning in voice recognition. In: 2021 3rd international congress on human-computer interaction, optimization and robotic applications (HORA). IEEE, pp 1\u20135"},{"key":"16200_CR10","unstructured":"Creative Commons (2018) Creative commons international attribution international 4.0 license. https:\/\/creativecommons.org\/licenses\/by\/4.0\/. Accessed 10 Aug 2022"},{"key":"16200_CR11","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/RAICS.2018.8635051","volume-title":"2018 IEEE recent advances in intelligent computational systems (RAICS)","author":"N Davis","year":"2018","unstructured":"Davis N, Suresh K (2018) Environmental sound classification using deep convolutional neural networks and data augmentation. In: 2018 IEEE recent advances in intelligent computational systems (RAICS). IEEE, pp 41\u201345"},{"key":"16200_CR12","first-page":"1","volume-title":"2019 International artificial intelligence and data processing symposium (IDAP)","author":"A Dem\u0131r","year":"2019","unstructured":"Dem\u0131r A, At\u0131la O, \u015eeng\u00fcr A (2019) Deep learning and audio based emotion recognition. In: 2019 International artificial intelligence and data processing symposium (IDAP). IEEE, pp 1\u20136"},{"issue":"4","key":"16200_CR13","first-page":"830","volume":"8","author":"MB ER","year":"2020","unstructured":"ER MB (2020) Akci\u011fer Seslerinin Derin \u00d6\u011frenme ile S\u0131n\u0131fland\u0131r\u0131lmas\u0131. Gazi University Journal of Science Part C: Design and Technology 8(4):830\u2013844","journal-title":"Gazi University Journal of Science Part C: Design and Technology"},{"issue":"5","key":"16200_CR14","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1016\/j.jvoice.2018.02.003","volume":"33","author":"S-H Fang","year":"2019","unstructured":"Fang S-H et al (2019) Detection of pathological voice using cepstrum vectors: a deep learning approach. J Voice 33(5):634\u2013641","journal-title":"J Voice"},{"issue":"3","key":"16200_CR15","first-page":"598","volume":"4","author":"D Gupta","year":"2015","unstructured":"Gupta D, Choubey S (2015) Discrete wavelet transform for image processing. Int J Emerg Technol Adv Eng 4(3):598\u2013602","journal-title":"Int J Emerg Technol Adv Eng"},{"key":"16200_CR16","volume-title":"Do\u011frusal \u00f6ng\u00f6r\u00fc ile konu\u015fma i\u015fareti kodlay\u0131c\u0131s\u0131 tasar\u0131m\u0131","author":"Y K\u0131r\u00e7i\u00e7ek","year":"2007","unstructured":"K\u0131r\u00e7i\u00e7ek Y (2007) Do\u011frusal \u00f6ng\u00f6r\u00fc ile konu\u015fma i\u015fareti kodlay\u0131c\u0131s\u0131 tasar\u0131m\u0131"},{"key":"16200_CR17","unstructured":"Kocer HE, Ahmed MC (2019) Turkish Speech recognition using Mel-frequency cepstral coefficients (MFCC) and Hidden Markov Model (HMM). Veri Bilimi 2(2):39\u201344"},{"key":"16200_CR18","doi-asserted-by":"crossref","unstructured":"Kumar Y, Gupta S, Singh W (2022) A novel deep transfer learning models for recognition of birds sounds in different environment.  Soft Computing (2022): 1\u201321","DOI":"10.1007\/s00500-021-06640-1"},{"key":"16200_CR19","unstructured":"Kurtkaya M (2021) Search Turkish speech command dataset about dataset. https:\/\/www.kaggle.com\/datasets\/muratkurtkaya\/turkish-speech-command-dataset. Accessed 15 Apr 2023"},{"key":"16200_CR20","doi-asserted-by":"publisher","first-page":"96162","DOI":"10.1109\/ACCESS.2020.2995737","volume":"8","author":"A Lauraitis","year":"2020","unstructured":"Lauraitis A, Maskeli\u016bnas R, Dama\u0161evi\u010dius R, Krilavi\u010dius T (2020) Detection of speech impairments using cepstrum, auditory spectrogram and wavelet time scattering domain features. IEEE Access 8:96162\u201396172","journal-title":"IEEE Access"},{"key":"16200_CR21","doi-asserted-by":"publisher","first-page":"57","DOI":"10.15439\/2019F185","volume-title":"2019 Federated conference on computer science and information systems (FedCSIS)","author":"I Lezhenin","year":"2019","unstructured":"Lezhenin I, Bogach N, Pyshkin E (2019) Urban sound classification using long short-term memory neural network. In: 2019 Federated conference on computer science and information systems (FedCSIS). IEEE, pp 57\u201360"},{"key":"16200_CR22","first-page":"1","volume-title":"2017 IEEE workshop on applications of signal processing to audio and acoustics (WASPAA)","author":"R Lu","year":"2017","unstructured":"Lu R, Duan Z, Zhang C (2017) Metric learning based data augmentation for environmental sound classification. In: 2017 IEEE workshop on applications of signal processing to audio and acoustics (WASPAA). IEEE, pp 1\u20135"},{"key":"16200_CR23","first-page":"1","volume-title":"2019 27th European signal processing conference (EUSIPCO)","author":"A Madhu","year":"2019","unstructured":"Madhu A, Kumaraswamy S (2019) Data augmentation using generative adversarial network for environmental sound classification. In: 2019 27th European signal processing conference (EUSIPCO). IEEE, pp 1\u20135"},{"key":"16200_CR24","doi-asserted-by":"publisher","first-page":"103085","DOI":"10.1016\/j.jisa.2021.103085","volume":"65","author":"J Mao","year":"2022","unstructured":"Mao J et al (2022) A novel model for voice command fingerprinting using deep learning. Journal of Information Security and Applications 65:103085","journal-title":"Journal of Information Security and Applications"},{"issue":"10","key":"16200_CR25","doi-asserted-by":"publisher","first-page":"2366","DOI":"10.3390\/cancers14102366","volume":"14","author":"R Maskeli\u016bnas","year":"2022","unstructured":"Maskeli\u016bnas R, Kulikajevas A, Dama\u0161evi\u010dius R, Pribui\u0161is K, Ulozait\u0117-Stanien\u0117 N, Uloza V (2022) Lightweight deep learning model for assessment of substitution voicing and speech after laryngeal carcinoma surgery. Cancers (Basel) 14(10):2366","journal-title":"Cancers (Basel)"},{"key":"16200_CR26","doi-asserted-by":"publisher","first-page":"101084","DOI":"10.1016\/j.ecoinf.2020.101084","volume":"57","author":"L Nanni","year":"2020","unstructured":"Nanni L, Maguolo G, Paci M (2020) Data augmentation approaches for improving animal audio classification. Ecol Inform 57:101084","journal-title":"Ecol Inform"},{"key":"16200_CR27","doi-asserted-by":"publisher","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","volume":"7","author":"AB Nassif","year":"2019","unstructured":"Nassif AB, Nassif AB, Shahin I, Attili I, Azzeh M, Shaalan K (2019) Speech recognition using deep neural networks: a systematic review. IEEE Access 7:19143\u201319165","journal-title":"IEEE Access"},{"key":"16200_CR28","first-page":"1","volume-title":"2015 IEEE 25th international workshop on machine learning for signal processing (MLSP)","author":"KJ Piczak","year":"2015","unstructured":"Piczak KJ (2015) Environmental sound classification with convolutional neural networks. In: 2015 IEEE 25th international workshop on machine learning for signal processing (MLSP). IEEE, pp 1\u20136"},{"key":"16200_CR29","first-page":"1","volume-title":"2019 international conference on creative business for smart and sustainable growth (CREBUS)","author":"S Pleshkova-Bekiarska","year":"2019","unstructured":"Pleshkova-Bekiarska S, Bekiarski A (2019) Building human mobile robot audio communication interface with artificial intelligence and deep learning. In: 2019 international conference on creative business for smart and sustainable growth (CREBUS). IEEE, pp 1\u20135"},{"key":"16200_CR30","unstructured":"R. Code (2018) Introduction to convolutional neural networks. https:\/\/rubikscode.net\/2018\/02\/26\/introduction-to-convolutional-neural-networks\/.\u00a0Accessed 10 Aug 2022"},{"issue":"1","key":"16200_CR31","first-page":"79","volume":"5","author":"NK Ravichandran","year":"2022","unstructured":"Ravichandran NK (2022) Tamil natural language voice classification using recurrent neural networks. Int J Res Eng Sci Manag 5(1):79\u201382","journal-title":"Int J Res Eng Sci Manag"},{"key":"16200_CR32","unstructured":"Shrawankar U, Thakare VM (2013) Techniques for feature extraction in speech recognition system: A comparative study. arXiv preprint arXiv:1305.1145"},{"key":"16200_CR33","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1109\/ELNANO50318.2020.9088863","volume-title":"2020 IEEE 40th international conference on electronics and nanotechnology (ELNANO)","author":"RA Solovyev","year":"2020","unstructured":"Solovyev RA et al (2020) Deep learning approaches for understanding simple speech commands. In: 2020 IEEE 40th international conference on electronics and nanotechnology (ELNANO). IEEE, pp 688\u2013693"},{"key":"16200_CR34","unstructured":"Speech Commands V2 (2018) http:\/\/download.tensorflow.org\/data\/speech_commands_v0.02.tar.gz.\u00a0Accessed 10 Aug 2022"},{"issue":"1","key":"16200_CR35","doi-asserted-by":"publisher","first-page":"19149","DOI":"10.1038\/s41598-021-98742-x","volume":"11","author":"P Suppakitjanusant","year":"2021","unstructured":"Suppakitjanusant P et al (2021) Identifying individuals with recent COVID-19 through voice classification using deep learning. Sci Rep 11(1):19149","journal-title":"Sci Rep"},{"key":"16200_CR36","unstructured":"Warden P (2018) Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16200-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16200-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16200-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T09:08:53Z","timestamp":1706692133000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16200-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,1]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["16200"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16200-4","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,1]]},"assertion":[{"value":"22 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}