Abstract
Estimating cepstral mean and variance normalization (CMVN) in run-on and real-time settings poses several challenges. Using a moving average for variance and mean estimation requires a comparatively long history of data from a speaker which is not appropriate for short utterances or conversations. Using a pre-estimated global CMVN for speakers instead reduces the recognition performance due to potential mismatch between training and testing data. This paper investigates how to build a real-time run-on speech recognition system using acoustic features without applying CMVN. We propose a feature extraction architecture which can transform unnormalized log mel features to normalized bottleneck features without using historical data. We empirically show that mean and variance normalization is not critical for training neural networks on speech data. Using the proposed feature extraction, we achieved 4.1% word error rate reduction compared to global CMVN on the Skype conversations test set. We also reveal many cases when features without zero-mean can be learnt well by neural networks which stands in contrast to prior work.
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
Alam, M.J., Ouellet, P., Kenny, P., O’Shaughnessy, D.: Comparative evaluation of feature normalization techniques for speaker verification. In: Travieso-González, C.M., Alonso-Hernández, J.B. (eds.) NOLISP 2011. LNCS (LNAI), vol. 7015, pp. 246–253. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25020-0_32
Cettolo, M., Niehues, J., Stüker, S., Bentivogli, L., Frederico, M.: Report on the 10th IWSLT evaluation campaign. In: The International Workshop on Spoken Language Translation (IWSLT) 2013 (2013)
Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788–798 (2011)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley-Interscience (2000)
Federmann, C., Lewis, W.D.: Microsoft speech language translation (MSLT) corpus: the IWSLT 2016 release for English, French and German. In: The International Workshop on Spoken Language Translation (IWSLT) 2016 (2016)
Finke, M., Geutner, P., Hild, H., Kemp, T., Ries, K.R., Westphal, M.: The karlsruhe VERBMOBIL speech recognition engine. In: Proceedings of ICASSP (1997)
Furui, S.: Cepstral analysis technique for automatic speaker verification. IEEE Trans. Acoust. Speech Signal Process. 29(2), 254–272 (1981)
Gehring, J., Miao, Y., Metze, F., Waibel, A.: Extracting deep bottleneck features using stacked auto-encoders. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3377–3381. IEEE (2013)
Graff, D.: The 1996 broadcast news speech and language-model corpus. In: Proceedings of the DARPA Workshop on Spoken Language Technology (1997)
Hannun, A., et al.: Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)
Jaitly, N., Hinton, G.E.: Vocal tract length perturbation (VTLP) improves speech recognition. In: Proceedings of ICML Workshop on Deep Learning for Audio, Speech and Language (2013)
Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: INTERSPEECH, pp. 3586–3589 (2015)
LeCun, Y.A., Bottou, L., Orr, G.B., Müller, K.-R.: Efficient backprop. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 9–48. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_3
Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: INTERSPEECH, pp. 3214–3218 (2015)
Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society, December 2011
Prisyach, T., Mendelev, V., Ubskiy, D.: Data augmentation for training of noise robust acoustic models. In: Ignatov, D.I., et al. (eds.) AIST 2016. CCIS, vol. 661, pp. 17–25. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52920-2_2
Pujol, P., Macho, D., Nadeu, C.: On real-time mean-and-variance normalization of speech recognition features. In: 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings, vol. 1, p. I. IEEE (2006)
Rousseau, A., Deléglise, P., Estève, Y.: Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks. In: Proceedings of LREC (2014)
Sainath, T.N., Kingsbury, B., Mohamed, A.R., Ramabhadran, B.: Learning filter banks within a deep neural network framework. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 297–302. IEEE (2013)
Sainath, T.N., Mohamed, A.R., Kingsbury, B., Ramabhadran, B.: Deep convolutional neural networks for LVCSR. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8614–8618. IEEE (2013)
Stüker, S., Kilgour, K., Kraft, F.: Quaero 2010 speech-to-text evaluation systems. In: Nagel, W., Kröner, D., Resch, M. (eds.) High Performance Computing in Science and Engineering ’11. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-23869-7_44
Viikki, O., Laurila, K.: Cepstral domain segmental feature vector normalization for noise robust speech recognition. Speech Commun. 25(1), 133–147 (1998)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: The 25th International Conference on Machine Learning, pp. 1096–1103. ACM (2008)
Yu, D., Seltzer, M.L.: Improved bottleneck features using pretrained deep neural networks. In: Interspeech, vol. 237, p. 240 (2011)
Zeiler, M.D., et al.: On rectified linear units for speech processing. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3517–3521. IEEE (2013)
Zeyer, A., Schlüter, R., Ney, H.: Towards online-recognition with deep bidirectional LSTM acoustic models. In: Interspeech 2016, pp. 3424–3428 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Nguyen, T.S., Sperber, M., Stüker, S., Waibel, A. (2018). Building Real-Time Speech Recognition Without CMVN. In: Karpov, A., Jokisch, O., Potapova, R. (eds) Speech and Computer. SPECOM 2018. Lecture Notes in Computer Science(), vol 11096. Springer, Cham. https://doi.org/10.1007/978-3-319-99579-3_47
Download citation
DOI: https://doi.org/10.1007/978-3-319-99579-3_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-99578-6
Online ISBN: 978-3-319-99579-3
eBook Packages: Computer ScienceComputer Science (R0)