ABSTRACT
In this paper has been discussed about speech recognition using spectrogram images and deep convolution neural network(CNN) of Uzbek spoken digits. Spectrogram images from speech signal were generated and it were used for deep CNN training. Presented CNN model contains 3 convolution layers and 2 fully connected layers that discriminative features can be divided and estimated of spectrogram images by those layers. In current research period, dataset of Uzbek spoken digits were made and in based on presented CNN model they were trained. Testing results shows that, proposed approach for Uzbek spoken digits classified 100% accuracy.
- A. Incze, Henrietta-Bernadette Jancsó, Z. Szilagyi, A. Farkas, C. Sulyok. Bird Sound Recognition Using a Convolutional Neural Network. SISY 2018 - IEEE 16th International Symposium on Intelligent Systems and Informatics, Proceedings. 2018, pp.295--300.Google ScholarCross Ref
- A.M. Badshah, J. Ahmad, N.Rahim, S.W.Baik. Speech Emotion Recognition from Spectrograms with Deep Convolutional Neural Network. 2017 International Conference on Platform Technology and Service, PlatCon 2017 - Proceedings.Google Scholar
- Adrian Rosebrock. Deep Learning for Computer Vision with Python Starter Bundle. 1st Edition (1.2.2). PyImageSearch.com. 2017.Google Scholar
- Al-Darkazali Mohammed. Image processing methods to segment speech spectrograms for word level recognition. Doctoral thesis (PhD), University of Sussex. (2017).Google Scholar
- Andrew Ng, Yan Zhang. Speech Recognition Using Deep Learning Algorithms. Published in 2013.Google Scholar
- B.D. Sarma, S.R.M. Prasanna. Acoustic--Phonetic Analysis for Speech Recognition: A Review. IETE Technical Review (Institution of Electronics and Telecommunication Engineers, India). 2018. pp.305--327.Google Scholar
- C. Glackin, J. Wall, G. Chollet, N. Dugan, N. Cannings. Convolutional neural networks for phoneme recognition. ICPRAM 2018 - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods. 2018. pp.190--195.Google ScholarCross Ref
- D. Polap, M. Woźniak. Image approach to voice recognition. 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. 2018. pp.1--7.Google Scholar
- Dennis, J., Tran, H. D., & Li, H. Spectrogram Image Feature for Sound Event Classification in Mismatched Conditions. IEEE Signal Processing Letters, 18(2), 130--133. doi:10.1109/lsp.2010.2100380.Google Scholar
- Diederik P. Kingma, Jimmy Lei Ba. ADAM: A Method for stochastic optimization. Published as a conference paper at ICLR 2015.Google Scholar
- Fisher, William M.; Doddington, George R.; Goudie-Marshall, Kathleen M. (1986). The DARPA Speech Recognition Research Database: Specifications and Status. pp. 93--99.Google Scholar
- Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevskiy, Ilya Sutskever, Ruslan R. Salakhutdinov. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research 15(1):1929--1958. June 2014.Google Scholar
- Gulmezoglu, M.B., et al., A novel approach to isolated word recognition. IEEE Transactions on Speech and Audio Processing, 1999. 7(6): p. 620--628.Google Scholar
- H. R. Hahnloser, R. Sarpeshkar, M. A. Mahowald, R. J. Douglas, & H. S. Seung, (2000). Erratum: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature, 405(6789), 947--951. doi:10.1038/35016072.Google Scholar
- Ibrahim Patel, Dr. Y. Srinivas Rao. Speech recognition using HMM with MFCC-an analysis using frequency Spectral decomposing technique. Signal & Image Processing: An International Journal (SIPIJ) Vol.1, No.2, December 2010.Google Scholar
- J. Ahmad;, M. Fiaz;, S.-i. Kwon;, M. Sodanil;, B. Vo;, and S. W. Baik, "Gender Identification using MFCC for Telephone Applications - A Comparative Study," International Journal of Computer Science and Electronics Engineering, vol. 3, pp. 351- 355, 2015.Google Scholar
- J. Baker, L. Deng, J. Glass, S. Khudanpur, Chin hui Lee, N. Morgan, and D. O'Shaughnessy, "Developments and directions in speech recognition and understanding, part 1," Signal Processing Magazine, IEEE, vol. 26, no. 3, pp. 75--80, may 2009.Google ScholarCross Ref
- J. Padmanabhan, M.J.J. Premkumar. Machine learning in automatic speech recognition: A survey. IETE Technical Review (Institution of Electronics and Telecommunication Engineers, India).2015. pp. 240--251.Google Scholar
- J. Zhang, S. Xiao, H. Zhang, L. Jiang. Isolated word recognition with audio derivation and CNN. Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI. 2018, pp. 336--341.Google Scholar
- Jaron Collis. "Glossary of Deep Learning: Batch Normalization". medium.com. Retrieved 24 April 2018.Google Scholar
- Klára, V., Viktor, I., Krisztina, M.: Voice disorder detection on the basis of continuous speech. In: 5th European Conference of the International Federation for Medical and Biological Engineering. Springer, Berlin (2011).Google Scholar
- Lonce Wyse. Audio Spectrogram Representations for Processing with Convolutional Neural Networks. Published 2017 in ArXiv.org.Google Scholar
- Longhao Yuan, Jianting Cao. Patients' EEG Data Analysis via Spectrogram Image with a Convolution Neural Network. Conference: International Conference on Intelligent Decision Technologies. DOI: 10.1007/978-3-319-59421-7_2.Google Scholar
- M Ahmadi, N J Bailey, B S Hoyle. Phoneme recognition using speech image (spectrogram). Published in IEEE: Proceedings of Third International Conference on Signal Processing (ICSP'96). doi: 10.1109/ICSIGP.1996.567353.Google Scholar
- M.M.Musaev, U.A.Berdanov, M.F.Rahimov, Shukurov K.E, "Parallel algorithms for acoustic processing of speech signals" International Conference on Signal and Image Processing (ICSIP 2016). China during August 13--15.Google Scholar
- Mark Gales, Steve Young. The Application of Hidden Markov Models in Speech Recognition. Foundations and Trends in Signal Processing Vol. 1, No. 3 (2007) 195--304.DOI: 10.1561/2000000004.Google ScholarDigital Library
- Mohamed O.M. Khelifa, Yahya Mohamed Elhadj, Yousfi Abdellah, Mostafa Belkasmi. Constructing accurate and robust HMM/GMM models for an Arabic speech recognition system. International Journal of Speech Technology. December 2017, Volume 20, Issue 4, pp 937--949.Google Scholar
- Ossama Abdel-Hamid, Abdel-rahman Mohamed, Hui Jiang, Li Deng, Gerald Penn, and Dong Yu. Convolutional Neural Networks for Speech Recognition. IEEE/ACM Transactions on Audio, speech, and language processing, vol. 22, NO. 10, October 2014.Google Scholar
- Q. T. Nguyen et al., "Speech classification using sift features on spectrogram images," Vietnam Journal of Computer Science, vol. 3, no. 4, pp. 247--257, 2016.Google ScholarDigital Library
- Rekik, S., Guerchi, D., Selouani, S.A., et al.: Speech steganography using wavelet and Fourier transforms. EURASIP J. Audio Speech Music Process. 2012(1), 20 (2012).Google ScholarCross Ref
- S. Chu, S. Narayanan, and C.-C. J. Kuo, "Environmental sound recognition with time--frequency audio features," IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, pp. 1142--1158, 2009.Google ScholarDigital Library
- Sergey Ioffe, Christian Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv.org > cs > arXiv:1502.03167.Google Scholar
- Sukmawati Nur Endah, Satriyo Adhy, Sutikno, Rizky Akbar. Automatic Speech Recognition for Indonesian using Linear Predictive Coding (LPC) and Hidden Markov Model (HMM). Proceeding of 5th International Seminar on New Paradigm and Innovation on Natural Science and Its Application (5th ISNPINSA), 7-8 October 2015, Semarang.Google Scholar
- Tungikar, V.V. and J. Mokashi, Study of Hidden Markov Model for Isolated Word Recognition. SYSTEM, 2016. 4(8).Google Scholar
- Venkatesh Boddapati, Andrej Petef, Jim Rasmusson, Lars Lundberg. Classifying environmental sounds using image recognition networks. December 2017. Procedia Computer Science 112:2048--2056. DOI: 10.1016/j.procs.2017.08.250.Google ScholarDigital Library
- Vinod Nair, Geoffrey E, Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair. Conference: Proceedings of the 27th International Conference on Machine Learning (ICML-10), June 21--24, 2010, Haifa, Israel.Google Scholar
- Waibel A. H, Hanazawa T, Hinton G, Shikano K, Lang K. "Phoneme Recognition Using Time-Delay Neural Networks.", IEEE Trans. on ASSP, Vol. ASSP-37, No. 3, March 1989.Google ScholarCross Ref
- Wang, S., Chen, X., Cai, G., et al.: Matching demodulation transform and synchro squeezing in time-frequency analysis. IEEE Trans. Signal Process. 62(1), 69--84 (2013).Google Scholar
- X. Glorot, A. Bordes, Y. Bengio. Deep Sparse Rectifier Neural Networks. Conference: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS). 2015.Google Scholar
- Yingying Li, Siyuan Pi, Nanfeng Xiao. Speech Recognition Method Based on Spectrogram. Proceedings of the International Conference on Mechatronics and Intelligent Robotics (ICMIR2017) - Volume 1.doi:10.1007/978-3-319-70990-1.Google Scholar
Index Terms
- Image Approach to Speech Recognition on CNN
Recommendations
Deep Learning for Robust Speech Command Recognition Using Convolutional Neural Networks (CNN)
IC3INA '22: Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its ApplicationsThe rapid development of mobile devices has made human-computer interaction through voice increasingly popular and effective. This condition is made possible by the rapid growth of Automatic Speech Recognition (ASR) technologies. ASR can convert human ...
Characterizing and detecting spontaneous speech: Application to speaker role recognition
Processing spontaneous speech is one of the many challenges that automatic speech recognition systems have to deal with. The main characteristics of this kind of speech are disfluencies (filled pause, repetition, false start, etc.) and many studies have ...
Speech-Input Speech-Output Communication for Dysarthric Speakers Using HMM-Based Speech Recognition and Adaptive Synthesis System
Dysarthria is a motor speech disorder that causes inability to control and coordinate one or more articulators. This makes it difficult for a dysarthric speaker to utter certain speech sound units, thereby producing poorly articulated, slurred, and ...
Comments