Abstract
This paper demonstrates how usual feature extraction methods such as the PLP can be successfully replaced by a neural network and how signal processing methods such as mean normalization, variance normalization and delta coefficients can be successfully utilized when a NN-based feature extraction and a NN-based acoustic model are used simultaneously. The importance of the deep NNs is also investigated. The system performance was evaluated on the British English speech corpus WSJCAM0.
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
Chang, S., Morgan, N.: Robust CNN-based speech recognition with Gabor filter kernels. In: 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), pp. 905–909, Singapore, September 14–18 (2014)
Astudillo, R.F., Abad, A., Trancoso, I.: Accounting for the residual uncertainty of multi-layer perceptron based features. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6859–6863, May 2014
Grézl, F., Karafiát, M.: Semi-supervised bootstrapping approach for neural network feature extractor training. In: ASRU, pp. 470–475. IEEE (2013)
Heřmanský, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 57(4), 1738–1752 (1990)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: CoRR abs/1502.03167 (2015)
Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7092–7096, May 2013
Pražák, A., Psutka, J.V., Psutka, J., Loose, Z.: Towards live subtitling of TV ice-hockey commentary. In: Cabello, E., Virvou, M., Obaidat, M.S., Ji, H., Nicopolitidis, P., Vergados, D.D. (eds.) SIGMAP, pp. 151–155. SciTePress (2013)
Psutka, J., Švec, J., Psutka, J.V., Vaněk, J., Pražák, A., Šmídl, L.: Fast phonetic/lexical searching in the archives of the czech holocaust testimonies: advancing towards the malach project visions. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2010. LNCS, vol. 6231, pp. 385–391. Springer, Heidelberg (2010)
Robinson, T., Fransen, J., Pye, D., Foote, J., Renals, S.: Wsjcam0: A british english speech corpus for large vocabulary continuous speech recognition. In: Proceedings of ICASSP 1995, pp. 81–84. IEEE (1995)
Sainath, T.N., Kingsbury, B., Mohamed, A.R., Ramabhadran, B.: Learning filter banks within a deep neural network framework. In: ASRU, pp. 297–302. IEEE (2013)
Sainath, T.N., Peddinti, V., Kingsbury, B., Fousek, P., Ramabhadran, B., Nahamoo, D.: Deep scattering spectra with deep neural networks for LVCSR tasks. In: 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), pp. 900–904, Singapore, September 14–18 (2014)
Seps, L., Málek, J., Cerva, P., Nouza, J.: Investigation of deep neural networks for robust recognition of nonlinearly distorted speech. In: Interspeech, pp. 363–367 (2014)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: CoRR abs/1409.4842 (2014)
Tüske, Z., Golik, P., Schlüter, R., Ney, H.: Acoustic modeling with deep neural networks using raw time signal for LVCSR. In: Interspeech, pp. 890–894, Singapore, September 2014
Acknowledgement
This research was supported by the Ministry of Culture Czech Republic, project No.DF12P01OVV022.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Zelinka, J., Salajka, P., Müller, L. (2015). On Deep and Shallow Neural Networks in Speech Recognition from Speech Spectrum. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds) Speech and Computer. SPECOM 2015. Lecture Notes in Computer Science(), vol 9319. Springer, Cham. https://doi.org/10.1007/978-3-319-23132-7_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-23132-7_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23131-0
Online ISBN: 978-3-319-23132-7
eBook Packages: Computer ScienceComputer Science (R0)