Abstract
The introduction of Deep Neural Network (DNN) based acoustic models has produced dramatic improvements in performance. In particular, we have recently found that Deep Maxout Networks, a modification of DNNs’ feed-forward architecture that uses a max-out activation function, provides enhanced robustness to environmental noise. In this paper we further investigate how these improvements are translated into the different broad phonetic classes and how does it compare to classical Hidden Markov Models (HMM) based back-ends. Our experiments demonstrate that performance is still tightly related to the particular phonetic class being stops and affricates the least resilient but also that relative improvements of both DNN variants are distributed unevenly across those classes having the type of noise a significant influence on the distribution. A combination of the different systems DNN and classical HMM is also proposed to validate our hypothesis that the traditional GMM/HMM systems have a different type of error than the Deep Neural Networks hybrid models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bourlard, H., Morgan, N.: Connectionist Speech Recognition: A Hybrid Approach. Kluwer International Series in Engineering and Computer Science: VLSI, Computer Architecture, and Digital Signal Processing. Springer, New York (1994)
de-la-Calle-Silos, F., Gallardo-Antolín, A., Peláez-Moreno, C.: Deep maxout networks applied to noise-robust speech recognition. In: Navarro Mesa, J.L., Ortega, A., Teixeira, A., Hernández Pérez, E., Quintana Morales, P., Ravelo García, A., Guerra Moreno, I., Toledano, D.T. (eds.) IberSPEECH 2014. LNCS (LNAI), vol. 8854, pp. 109–118. Springer, Heidelberg (2014). doi:10.1007/978-3-319-13623-3_12
Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30–42 (2012)
Deng, L., Yu, D., Acero, A.: Structured speech modeling. IEEE Trans. Audio Speech Lang. Process. 14(5), 1492–1504 (2006)
Fiscus, J.G.: A post-processing system to yield reduced word error rates: recognizer output voting error reduction (ROVER). In: Proceedings of 1997 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 347–354, December 1997
Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S., Dahlgren, N.L.: DARPA TIMIT acoustic phonetic continuous speech corpus CDROM (1993)
Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. arXiv e-prints, February 2013
Hinton, G.E.: A practical guide to training restricted Boltzmann machines. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, 2nd edn, pp. 599–619. Springer, Heidelberg (2012). doi:10.1007/978-3-642-35289-8_32
Hinton, G.E., Deng, L., Yu, D., Dahl, G.E., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29(6), 82–97 (2012)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. CoRR (2012)
Hirsch, G.: Fant - filtering and noise adding tool (2005). http://dnt.kr.hsnr.de/download.html
Kim, C., Stern, R.M.: Power-normalized cepstral coefficients (PNCC) for robust speech recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 24(7), 1315–1329 (2016). doi:10.1109/TASLP.2016.2545928
Li, J., Deng, L., Gong, Y., Haeb-Umbach, R.: An overview of noise-robust automatic speech recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 22(4), 745–777 (2014)
Miao, Y.: Kaldi+PDNN: building DNN-based ASR systems with Kaldi and PDNN. CoRR (2014)
Miao, Y., Metze, F., Rawat, S.: Deep maxout networks for low-resource speech recognition. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, 8–12 December 2013
Mohamed, A., Dahl, G.E., Hinton, G.E.: Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process. 20(1), 14–22 (2012)
Morgan, N.: Deep and wide: multiple layers in automatic speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 7–13 (2012)
Peláez-Moreno, C., García-Moral, A.I., Valverde-Albacete, F.J.: Analyzing phonetic confusions using formal concept analysis. J. Acoust. Soc. Am. 128(3), 1377–1390 (2010)
Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society, December 2011
Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2013)
Tóth, L.: Convolutional deep maxout networks for phone recognition. In: INTERSPEECH, pp. 1078–1082. ISCA (2014)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)
Wan, L., Zeiler, M.D., Zhang, S., LeCun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: Proceedings of 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16–21 June 2013
Acknowledgements
This contribution has been supported by an Airbus Defense and Space Grant (Open Innovation - SAVIER) and Spanish Government-CICYT project TEC2014-53390-P. We would also like to thank Chanwoo Kim for kindly providing the testing noises.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
de-la-Calle-Silos, F., Gallardo-Antolín, A., Peláez-Moreno, C. (2016). An Analysis of Deep Neural Networks in Broad Phonetic Classes for Noisy Speech Recognition. In: Abad, A., et al. Advances in Speech and Language Technologies for Iberian Languages. IberSPEECH 2016. Lecture Notes in Computer Science(), vol 10077. Springer, Cham. https://doi.org/10.1007/978-3-319-49169-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-49169-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49168-4
Online ISBN: 978-3-319-49169-1
eBook Packages: Computer ScienceComputer Science (R0)