{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:34:10Z","timestamp":1778344450544,"version":"3.51.4"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s10772-023-10019-y","type":"journal-article","created":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T21:19:18Z","timestamp":1677014358000},"page":"287-305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["An approach for speech enhancement with dysarthric speech recognition using optimization based machine learning frameworks"],"prefix":"10.1007","volume":"26","author":[{"given":"Bhuvaneshwari","family":"Jolad","sequence":"first","affiliation":[]},{"given":"Rajashri","family":"Khanai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,21]]},"reference":[{"issue":"1","key":"10019_CR1","first-page":"9","volume":"2","author":"JS Anita","year":"2019","unstructured":"Anita, J. S., & Abinaya, J. S. (2019). Impact of supervised classifier on speech emotion recognition. Multimedia Research, 2(1), 9\u201316.","journal-title":"Multimedia Research"},{"issue":"1","key":"10019_CR2","first-page":"37","volume":"2","author":"V Arul","year":"2019","unstructured":"Arul, V., Sivakumar, V. G., Marimuthu, R., & Chakraborty, B. (2019). An approach for speech enhancement using deep convolutional neural network. Multimedia Research, 2(1), 37\u201344.","journal-title":"Multimedia Research"},{"key":"10019_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.compstruc.2016.03.001","volume":"169","author":"A Askarzadeh","year":"2016","unstructured":"Askarzadeh, A. (2016). A novel metaheuristic method for solving constrained engineering optimization problems: Crow search algorithm. Computers and Structures, 169, 1\u201312.","journal-title":"Computers and Structures"},{"key":"10019_CR4","doi-asserted-by":"crossref","unstructured":"Bhaladhare, P. R., & Jinwala, D. C. (2014). A clustering approach for the -diversity model in privacypreserving data mining using fractional calculus-bacterial. Advances in Computer Engineering.","DOI":"10.1155\/2014\/396529"},{"issue":"2","key":"10019_CR5","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1109\/TCYB.2014.2322602","volume":"45","author":"R Cheng","year":"2014","unstructured":"Cheng, R., & Jin, Y. (2014). A competitive swarm optimizer for large scale optimization. IEEE Transactions on Cybernetics, 45(2), 191\u2013204.","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"2","key":"10019_CR6","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1007\/s11277-019-06902-0","volume":"111","author":"TK Dash","year":"2020","unstructured":"Dash, T. K., & Solanki, S. S. (2020). Speech intelligibility based enhancement system using modified deep neural network and adaptive multi-band spectral subtraction. Wireless Personal Communications, 111(2), 1073\u20131087.","journal-title":"Wireless Personal Communications"},{"key":"10019_CR7","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/B978-0-444-52901-5.00022-8","volume":"110","author":"P Enderby","year":"2013","unstructured":"Enderby, P. (2013). Disorders of communication: Dysarthria. Handbook of Clinical Neurology, 110, 273\u2013281.","journal-title":"Handbook of Clinical Neurology"},{"issue":"2","key":"10019_CR8","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s10772-018-9494-9","volume":"21","author":"OS Faragallah","year":"2018","unstructured":"Faragallah, O. S. (2018). Robust noise MKMFCC\u2013SVM automatic speaker identification. International Journal of Speech Technology, 21(2), 185\u2013192.","journal-title":"International Journal of Speech Technology"},{"key":"10019_CR9","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/LSP.2021.3050362","volume":"28","author":"J Fritsch","year":"2021","unstructured":"Fritsch, J., & Magimai-Doss, M. (2021). Utterance verification-based dysarthric speech intelligibility assessment using phonetic posterior features. IEEE Signal Processing Letters, 28, 224\u2013228.","journal-title":"IEEE Signal Processing Letters"},{"issue":"3","key":"10019_CR10","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/j.jksuci.2014.04.006","volume":"27","author":"A Garg","year":"2015","unstructured":"Garg, A., & Sahu, O. P. (2015). Cuckoo search based optimal mask generation for noise suppression and enhancement of speech signal. Journal of King Saud University-Computer and Information Sciences, 27(3), 269\u2013277.","journal-title":"Journal of King Saud University-Computer and Information Sciences"},{"key":"10019_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2020.04.006","volume":"121","author":"K Gurugubelli","year":"2020","unstructured":"Gurugubelli, K., & Vuppala, A. K. (2020). Analytic phase features for dysarthric speech detection and intelligibility assessment. Speech Communication, 121, 1\u201315.","journal-title":"Speech Communication"},{"issue":"7-8","key":"10019_CR12","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1080\/01969722.2018.1448241","volume":"49","author":"AV Haridas","year":"2018","unstructured":"Haridas, A. V., Marimuthu, R., & Chakraborty, B. (2018). A novel approach to improve the speech intelligibility using fractional delta-amplitude modulation spectrogram. Cybernetics and Systems, 49(7\u20138), 421\u2013451.","journal-title":"Cybernetics and Systems"},{"key":"10019_CR14","doi-asserted-by":"crossref","unstructured":"Hasegawa-Johnson, M., Gunderson, J., Perlman, A., & Huang, T. (2006). HMM-based and SVM-based recognition of the speech of talkers with spastic dysarthria. In IEEE international conference on acoustics speech and signal processing proceedings (Vol. 3).","DOI":"10.1109\/ICASSP.2006.1660840"},{"issue":"3","key":"10019_CR15","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1109\/TASLP.2016.2636445","volume":"25","author":"Q He","year":"2016","unstructured":"He, Q., Bao, F., & Bao, C. (2016). Multiplicative update of auto-regressive gains for codebook-based speech enhancement. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 25(3), 457\u2013468.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"10019_CR16","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2007","unstructured":"Hu, Y., & Loizou, P. C. (2007). Evaluation of objective quality measures for speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing, 16(1), 229\u2013238.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"10019_CR17","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.specom.2006.12.006","volume":"49","author":"Y Hu","year":"2017","unstructured":"Hu, Y., & Loizou, P. C. (2017). NOIZEUS: A noisy speech corpus for evaluation of speech enhancement algorithms. Speech Communication, 49, 588\u2013601.","journal-title":"Speech Communication"},{"key":"10019_CR18","doi-asserted-by":"crossref","unstructured":"Jain, U., Nathani, K., Ruban, N., Raj, A. N. J., Zhuang, Z., & Mahesh, V. G. (2018) Cubic SVM classifier based feature extraction and emotion detection from speech signals. In IEEE International Conference on Sensor Networks and Signal Processing (SNSP) (pp. 386\u2013391).","DOI":"10.1109\/SNSP.2018.00081"},{"issue":"1","key":"10019_CR19","doi-asserted-by":"crossref","first-page":"146045821989385","DOI":"10.1177\/1460458219893850","volume":"27","author":"PF KhaleelurRahiman","year":"2021","unstructured":"KhaleelurRahiman, P. F., Jayanthi, V. S., & Jayanthi, A. N. (2021). Speech enhancement method using deep learning approach for hearing-impaired listeners. Health Informatics Journal, 27(1), 1460458219893850.","journal-title":"Health Informatics Journal"},{"issue":"7-8","key":"10019_CR20","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.specom.2006.12.006","volume":"49","author":"P Loizou","year":"2007","unstructured":"Loizou, P. (2007). Subjective comparison and evaluation of speech enhancement algorithms. Speech Communication, 49(7\u20138), 588\u2013601.","journal-title":"Speech Communication"},{"issue":"5","key":"10019_CR21","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TSA.2005.851927","volume":"13","author":"R Martin","year":"2005","unstructured":"Martin, R. (2005). Speech enhancement based on minimum mean-square error estimation and supergaussian priors. IEEE Transactions on Speech and Audio Processing, 13(5), 845\u2013856.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"10019_CR22","doi-asserted-by":"publisher","first-page":"101117","DOI":"10.1016\/j.csl.2020.101117","volume":"65","author":"NP Narendra","year":"2021","unstructured":"Narendra, N. P., & Alku, P. (2021). Automatic assessment of intelligibility in speakers with dysarthria from coded telephone speech using glottal features. Computer Speech & Language, 65, 101117.","journal-title":"Computer Speech & Language"},{"key":"10019_CR23","doi-asserted-by":"crossref","unstructured":"Pascual, S., Bonafonte, A., & Serra, J. (2017). SEGAN: Speech enhancement generative adversarial network. arXiv preprint arXiv:1703.09452.","DOI":"10.21437\/Interspeech.2017-1428"},{"issue":"8","key":"10019_CR24","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1016\/j.medengphy.2005.11.002","volume":"28","author":"PD Polur","year":"2006","unstructured":"Polur, P. D., & Miller, G. E. (2006). Investigation of an HMM\/ANN hybrid structure in pattern recognition application using cepstral analysis of dysarthric (distorted) speech signals. Medical Engineering & Physics, 28(8), 741\u2013748.","journal-title":"Medical Engineering & Physics"},{"key":"10019_CR25","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/TNSRE.2021.3076778","volume":"29","author":"SR Shahamiri","year":"2021","unstructured":"Shahamiri, S. R. (2021). Speech vision: An end-to-end deep learning-based dysarthric automatic speech recognition system. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29, 852\u2013861.","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"10019_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-019-0169-5","volume":"1","author":"M Sidi Yakoub","year":"2020","unstructured":"Sidi Yakoub, M., Selouani, S. A., Zaidi, B. F., & Bouchair, A. (2020). Improving dysarthric speech recognition using empirical mode decomposition and convolutional neural network. EURASIP Journal on Audio, Speech, and Music Processing, 1, 1\u20137.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"10019_CR27","doi-asserted-by":"crossref","unstructured":"Takashima, Y., Takashima, R., Takiguchi, T., & Ariki, Y. (2020). Dysarthric speech recognition based on deep metric learning. In Interspeech (pp. 4796\u20134800).","DOI":"10.21437\/Interspeech.2020-2267"},{"key":"10019_CR31","unstructured":"The UA speech database will be taken from http:\/\/www.isle.illinois.edu\/sst\/data\/UASpeech\/. Retrieved August 2021."},{"key":"10019_CR28","doi-asserted-by":"crossref","unstructured":"Trinh, V. A., & Braun, S. (2021). Unsupervised speech enhancement with speech recognition embedding and disentanglement losses. arXiv:2111.08678 [eess.AS]","DOI":"10.1109\/ICASSP43922.2022.9746973"},{"key":"10019_CR29","first-page":"1","volume":"1","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Han, J., Zhang, T., & Qing, D. (2021). Speech enhancement from fused features based on deep neural network and gated recurrent unit network. EURASIP Journal on Advances in Signal Processing, 1, 1\u201319.","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"10019_CR30","doi-asserted-by":"crossref","unstructured":"Welker, S., Richter, J., & Gerkmann, T. (2022). Speech enhancement with score-based generative models in the complex STFT domain. arXiv:2203.17004 [eess.AS]","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"10019_CR32","doi-asserted-by":"crossref","unstructured":"Woszczyk, D., Petridis, S., & Millard, D. (2020). Domain adversarial neural networks for dysarthric speech recognition. arXiv preprint arXiv:2010.03623","DOI":"10.21437\/Interspeech.2020-2845"},{"key":"10019_CR33","unstructured":"Xiong, F., Barker, J., & Christensen, H. (2018). Deep learning of articulatory-based representations and applications for improving dysarthric speech recognition. In 13th ITG-symposium on speech communication (pp. 1\u20135)."},{"key":"10019_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., & Hovy, E. (2016). Hierarchical attention networks for document classification. In Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: Human language technologies (pp. 1480\u20131489)","DOI":"10.18653\/v1\/N16-1174"},{"key":"10019_CR35","doi-asserted-by":"crossref","unstructured":"Yu, J., Xie, X., Liu, S., Hu, S., Lam, M. W., Wu, X., Wong, K. H., Liu, X., & Meng, H. (2018). Development of the CUHK dysarthric speech recognition system for the UA speech corpus. In Interspeech (pp. 2938\u20132942).","DOI":"10.21437\/Interspeech.2018-1541"},{"key":"10019_CR36","doi-asserted-by":"crossref","unstructured":"Yue, Z., Christensen, H., & Barker, J. (2020). Autoencoder bottleneck features with multi-task optimisation for improved continuous dysarthric speech recognition. In Proceedings of the annual conference of the international speech communication association, international speech communication association (ISCA).","DOI":"10.21437\/Interspeech.2020-2746"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10019-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-023-10019-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10019-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T11:15:45Z","timestamp":1690802145000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-023-10019-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,21]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["10019"],"URL":"https:\/\/doi.org\/10.1007\/s10772-023-10019-y","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,21]]},"assertion":[{"value":"30 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}