Abstract
Multi-condition training achieved through data augmentation belongs to the most successful techniques for noise/reverberation-robust automatic speech recognition (ASR). Its basic principle, i.e., generation of artificially distorted speech signals, is well documented in the literature. However, the specific choice of hyper-parameters for the generation process and its influence on the results of the subsequent ASR is usually not discussed in detail. Often, it is simply assumed that the augmentation should include as many acoustic conditions as possible. When designed in this broad manner, the computational/storage demands of the augmentation process grow rapidly.
In this paper, we rather aim for careful selection of a limited number of acoustic conditions that are highly relevant with respect to the target environment. In this manner, we keep the computational requirements feasible, while retaining the improved accuracy of the augmented models. We experimentally analyze two augmentation scenarios and draw conclusions regarding suitable setup choices. The first case concerns augmentation for reverberation-robust ASR. We propose to exploit Clarity \(C_{50}\) as a feature for selection of Room Impulse Responses (RIRs) crucial for the augmentation. We show that mismatches in other RIR-related parameters, such as Reverberation Time \(T_{60}\) or the room dimension, have small influence on ASR accuracy, as long as the training-test conditions are matched from the \(C_{50}\) perspective. Subsequently, we investigate the augmentation for noise-reverberation-robust ASR. We discuss selection of Signal-to-Noise Ratio (SNR), the type of noise and reverberation level of speech. We observe the influence of mismatches in these parameters on the ASR accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Boll, S.: Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust. Speech Signal Process. 27(2), 113–120 (1979)
Brutti, A., Matassoni, M.: On the relationship between early-to-late ratio of room impulse responses and asr performance in reverberant environments. Speech Commun. 76, 170–185 (2016)
Cui, X., Goel, V., Kingsbury, B.: Data augmentation for deep neural network acoustic modeling. IEEE/ACM Trans. Audio Speech Lang. Process. (TASLP) 23(9), 1469–1477 (2015)
Dahl, G., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 20(1), 30–42 (2012)
DCASE Community: DCASE 2018 challenge. http://dcase.community/challenge2018/index. Accessed 5 December 2018
Ephraim, Y., Malah, D.: Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Trans. Acoust. Speech Signal Process. 32(6), 1109–1121 (1984)
Ferras, M., Madikeri, S., Motlicek, P., Dey, S., Bourlard, H.: A large-scale open-source acoustic simulator for speaker recognition. IEEE Signal Process. Lett. 23(4), 527–531 (2016)
Gannot, S., Vincent, E., Markovich-Golan, S., Ozerov, A.: A consolidated perspective on multimicrophone speech enhancement and source separation. IEEE/ACM Trans. Audio Speech Lang. Process. 25(4), 692–730 (2017)
Giri, R., Seltzer, M.L., Droppo, J., Yu, D.: Improving speech recognition in reverberation using a room-aware deep neural network and multi-task learning. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5014–5018. IEEE (2015)
Habets, E.A.: Room impulse response generator. Technische Universiteit Eindhoven, Technical Report 2(2.4), 1 (2006)
Hadad, E., Heese, F., Vary, P., Gannot, S.: Multichannel audio database in various acoustic environments. In: 2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC), pp. 313–317. IEEE (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, pp. 625–660 (2013)
Kim, C., et al.: Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google home. In: Proceedings of INTERSPEECH, ISCA (2017)
Kneser, R., Ney, H.: Improved backing-off for m-gram language modeling. In: 1995 International Conference on Acoustics, Speech, and Signal Processing, ICASSP-1995, vol. 1, pp. 181–184. IEEE (1995)
Ko, T., Peddinti, V., Povey, D., Seltzer, M.L., Khudanpur, S.: A study on data augmentation of reverberant speech for robust speech recognition. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5220–5224. IEEE (2017)
Kuttruff, H.: Room Acoustics. CRC Press, Boca Raton (2016)
Li, J., Seltzer, M.L., Wang, X., Zhao, R., Gong, Y.: Large-scale domain adaptation via teacher-student learning. arXiv preprint arXiv:1708.05466 (2017)
Makino, S., Lee, T.W., Sawada, H.: Blind Speech Separation, vol. 615. Springer, Switzerland (2007). https://doi.org/10.1007/978-1-4020-6479-1
Málek, J., Ždánský, J., Červa, P.: Robust recognition of conversational telephone speech via multi-condition training and data augmentation. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2018. LNCS (LNAI), vol. 11107, pp. 324–333. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00794-2_35
Mammone, R.J., Zhang, X., Ramachandran, R.P.: Robust speaker recognition: a feature-based approach. IEEE Signal Process. Mag. 13(5), 58 (1996)
Mirsamadi, S., Hansen, J.H.: A study on deep neural network acoustic model adaptation for robust far-field speech recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)
Parada, P.P., Sharma, D., Lainez, J., Barreda, D., van Waterschoot, T., Naylor, P.A.: A single-channel non-intrusive c50 estimator correlated with speech recognition performance. IEEE/ACM Trans. Audio Speech Lang. Process. (TASLP) 24(4), 719–732 (2016)
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
Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7398–7402. IEEE (2013)
Torch team: torch - a scientific computing framework for luajit. http://torch.ch. Accessed 5 December 2018
Wang, D., Chen, J.: Supervised speech separation based on deep learning: an overview. IEEE/ACM Trans. Audio Speech Lang. Process. 26, 1702–1726 (2018)
Xu, Y., Du, J., Dai, L.R., Lee, C.H.: Dynamic noise aware training for speech enhancement based on deep neural networks. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)
Young, S., Young, S.: The HTK hidden Markov model toolkit: design and philosophy. Entropic Cambridge Research Laboratory, Ltd. vol. 2, pp. 2–44 (1994)
Zhang, Z., Geiger, J., Pohjalainen, J., Mousa, A.E.D., Jin, W., Schuller, B.: Deep learning for environmentally robust speech recognition: an overview of recent developments. ACM Trans. Intell. Syst. Technol. (TIST) 9(5), 49 (2018)
Acknowledgments
This work was supported by the Technology Agency of the Czech Republic (Project No. TH03010018).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Malek, J., Zdansky, J. (2019). On Practical Aspects of Multi-condition Training Based on Augmentation for Reverberation-/Noise-Robust Speech Recognition. In: Ekštein, K. (eds) Text, Speech, and Dialogue. TSD 2019. Lecture Notes in Computer Science(), vol 11697. Springer, Cham. https://doi.org/10.1007/978-3-030-27947-9_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-27947-9_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27946-2
Online ISBN: 978-3-030-27947-9
eBook Packages: Computer ScienceComputer Science (R0)