Abstract
This paper aims to classify noisy sound samples in several daily indoor and outdoor acoustic scenes using an optimized deep neural networks (DNNs). The advantage of a traditional DNNs lies in using at the top layer a softmax activation function which is a logistic regression in order to learn the output label in a multi-class recognition problem. In this paper, we optimize the DNNs by replacing the softmax activation function by a linear support vector machine.
In this paper, a novel deep neural networks (DN) using Support Vector Machines (SVM) instead of the multinomial logistic regression is proposed. We have verified the effectiveness of this new method using speech samples from Aurora speech database recorded in noisy conditions. The experimental results obtained with the method DN-SVM demonstrates a significant improvement of the performance with noisy sound samples classification.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Hemsoth, N.: The next wave of deep learning applications. Next Platform, September 2016
Sze, V., Yu-Hsin Chen, Y.H., Yang, T.J., Fellow, J.E.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295–2329 (2017)
Mohamed, A., Dahl, G.E., Hinton, G.E.: Deep belief networks for phone recognition. In: NIPS Workshop on Deep Learning for Speech Recognition and Related Applications (2009)
Quoc, L., Ngiam, J., Chen, Z., Chia, D., Koh, P.W., Ng, A.: Tiled convolutional neural networks. In: NIPS 23 (2010)
Dhal, G.E., Ranzato, M., Mohamed, A., Hinton, G.E.: Phone recognition with the mean-covariance restricted Boltzmann machine. In: Neural Information Processing Systems Conference 23 (2010)
Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition. In: Proceedings International Conference on Computer Vision (ICCV09). IEEE (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995). 8(6), 188
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Schölkopf, B., Burges, C., Vapnik, V.: Extracting support data for a given task. In: Conference on Knowledge Discovery and Data Mining (1995)
Li, L., Zhao, Y., Jiang, D., Zhang, Y., Wang, F., Gonzalez, I., Valentin, E., Sahli, H.: Hybrid deep neural network-hidden markov model (DNN-HMM) based speech emotion recognition. In: Proceedings of the 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction, pp. 312–317 (2013)
Yu, D., Deng, L.: Deep neural network-hidden markov model hybrid systems. In: Automatic Speech Recognition. Signals and Communication Technology. Springer, London (2015)
Zhang, S.X., Liu, C., Yao, K., Gong, Y.: Deep neural support vector machines for speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2015)
Tang, Y.: Deep learning using linear support vector machines. In: International Conference on Machine Learning Challenges in Representation Learning Workshop, Atlanta, Georgia, USA (2013)
Zhu, Q., Iseli, M., Cui, X., Alwan, A.: Noise robust feature extraction for asr using the aurora 2 database. In: 7th European Conference on Speech Communication and Technology, 2nd INTERSPEECH Event, Aalborg, Denmark, 3–7 September 2001
Hirsch, H.G., Pearce, D.: The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy condition. In: ISCA ITRW ASR 2000 Automatic Speech Recognition: Challenges for the Next Millennium, France (2000)
Amami, R., Ben Ayed, D., Ellouze, N.: Phoneme recognition using support vector machine and different features representations. In: The 9th International Conference Distributed Computing and Artificial Intelligence (DCAI). Advances in Intelligent and Soft Computing, vol. 151, pp. 587–595, Salamanca, Spain. Springer, Heidelberg (2012)
Davis, S.B., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. Acoust. Speech Sig. Process. 28(4), 357–366 (1980)
Deng, L., Li, J., Huang, J.-T., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, X., Williams, J., et al.: Recent advances in deep learning for speech research at Microsoft. In: ICASSP (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Amami, R., Ben Ayed, D. (2019). Robust Noisy Speech Recognition Using Deep Neural Support Vector Machines. In: De La Prieta, F., Omatu, S., Fernández-Caballero, A. (eds) Distributed Computing and Artificial Intelligence, 15th International Conference. DCAI 2018. Advances in Intelligent Systems and Computing, vol 800. Springer, Cham. https://doi.org/10.1007/978-3-319-94649-8_36
Download citation
DOI: https://doi.org/10.1007/978-3-319-94649-8_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-94648-1
Online ISBN: 978-3-319-94649-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)