Abstract
The Iris, face, fingers, conduct, voice, and other things of the human body are employed for security and identification since they are unique in each person. Biometric systems are popular and widely used in Bangladesh to identify people, e.g. in cybercrime. Apart from biometrics, a person can be identified by their voice. Since each person’s speech has a distinct timbre, vocal pattern, and frequency spectrogram. A human can easily identify the voice of a known person, but it is difficult for a machine. As a result, researchers are interested in processing human voices and recognizing them by machines. To predict the human voice, various traditional machine learning models such as GMM, HMM, SVM, and MLP are used. Voice data is a complex time-series signal and massive datasets are required to train ML models. As a result, traditional ML has low accuracy and takes a long time to train. In contrast, LSTM neural networks, which are the branch of ML, require less time to train a model with high accuracy. This paper focuses on an LSTM network for identifying a person based on Bangla speech because the Bangla language has 50 alphabets and their pronunciation differs from other languages such as English and Chinese. We extracted features from Bangla Voice using MFCCs. Our proposed model’s performance is measured using the K-fold validation, accuracy, precision, recall, and F1 score. Experimental results of our proposed model achieved a high recognition accuracy of 99.98%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chakroborty, S., Saha, G.: Improved text-independent speaker identification using fused MFCC & IMFCC feature sets based on gaussian filter. Int. J. Signal Process. 5(1), 11–19 (2009)
colah: Understanding LSTM networks (2015). http://colah.github.io/posts/2015-08-Understanding-LSTMs/
Ertam, F.: An effective gender recognition approach using voice data via deeper LSTM networks. Appl. Acoust. 156, 351–358 (2019)
Karatas, T., Hirsa, A.: Two-stage sector rotation methodology using machine learning and deep learning techniques. arXiv preprint arXiv:2108.02838 (2021)
Krishnamoorthy, P., Jayanna, H., Prasanna, S.M.: Speaker recognition under limited data condition by noise addition. Expert Syst. Appl. 38(10), 13487–13490 (2011)
Livieris, I.E., Pintelas, E., Pintelas, P.: Gender recognition by voice using an improved self-labeled algorithm. Mach. Learn. Knowl. Extract. 1(1), 492–503 (2019)
Lukic, Y., Vogt, C., Dürr, O., Stadelmann, T.: Speaker identification and clustering using convolutional neural networks. In: 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1–6. IEEE (2016)
Olugbenga, T.O.: Deep learning techniques for electrical load forecasting. Ph.D. thesis, University of New Brunswick (2022)
Pondhu, L.N., Kummari, G.: Performance analysis of machine learning algorithms for gender classification. In: 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), pp. 1626–1628. IEEE (2018)
Reynolds, D.A., Rose, R.C.: Robust text-independent speaker identification using gaussian mixture speaker models. IEEE Trans. Speech Audio Process. 3(1), 72–83 (1995)
Saeidi, R., et al.: Signal-to-signal ratio independent speaker identification for co-channel speech signals. In: 2010 20th International Conference on Pattern Recognition, pp. 4565–4568. IEEE (2010)
Shahin, I.: Speaker identification in emotional environments (2009)
Sharma, G., Umapathy, K., Krishnan, S.: Trends in audio signal feature extraction methods. Appl. Acoust. 158, 107020 (2020)
Shewalkar, A.: Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU. J. Artif. Intell. Soft Comput. Res. 9(4), 235–245 (2019)
Stamp, M., Alazab, M., Shalaginov, A.: Malware Analysis Using Artificial Intelligence and Deep Learning. Springer, Heidelberg (2021). https://doi.org/10.1007/978-3-030-62582-5
Tandel, N.H., Prajapati, H.B., Dabhi, V.K.: Voice recognition and voice comparison using machine learning techniques: a survey. In: 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS), pp. 459–465. IEEE (2020)
Ye, F., Yang, J.: A deep neural network model for speaker identification. Appl. Sci. 11(8), 3603 (2021)
Zhao, Y., Miao, R.: Network media public opinion and social governance supported by the internet-of-things big data. Secur. Commun. Netw. 2022 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Khan, R., Hossain, S., Hossain, A., Siddiqui, F.H., Noor, S.B. (2023). Bangla Speech-Based Person Identification Using LSTM Networks. In: Satu, M.S., Moni, M.A., Kaiser, M.S., Arefin, M.S. (eds) Machine Intelligence and Emerging Technologies. MIET 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 490. Springer, Cham. https://doi.org/10.1007/978-3-031-34619-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-34619-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34618-7
Online ISBN: 978-3-031-34619-4
eBook Packages: Computer ScienceComputer Science (R0)