Abstract
In this paper we propose a method for estimating speaking rate by means of Deep Neural Networks (DNN). The proposed approach is used for speaking rate adaptation of an automatic speech recognition system. The adaptation is performed by changing step in front-end feature processing according to the estimations of speaking rate. Experiments show that adaptation results using the proposed DNN-based speaking rate estimator are better than the results of adaptation using the speaking rate estimator based on the recognition results.
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
Preview
Unable to display preview. Download preview PDF.
References
Mirghafori, N., Fosler, E., Morgan, N.: Towards robustness to fast speech in ASR. In: Proc. of the IEEE International Conference in Acoustics, Speech, and Signal Processing, ICASSP 1996, pp. 335–338 (1996)
Morgan, N., Fosler-Lussier, E.: Combining multiple estimators of speaking rate. In: Proc. of the IEEE International Conference In Acoustics, Speech, and Signal Processing, ICASSP-1996, pp. 729–732 (1998)
Faltlhauser, R., Pfau, T., Ruske, G.: On-line speaking rate estimation using gaussian mixture models. In: Proc. of the IEEE International Conference In Acoustics, Speech, and Signal Processing, ICASSP 2000, pp. 1355–1358 (2000)
Pfau, T., Ruske, G.: Estimating the speaking rate by vowel detection. In: Proc. of the IEEE International Conference In Acoustics, Speech and Signal Processing, ICASSP 1998, pp. 945–948 (1998)
Mirghafori, N., Foster, E., Morgan, N.: Fast speakers in large vocabulary continuous speech recognition: analysis & antidotes. In: Proc. of the EUROSPEECH, pp. 491–494 (1995)
Siegler, M.A.: Measuring and compensating for the effects of speech rate in large vocabulary continuous speech recognition (PhD Thesis). Carnegie Mellon University, Pittsburgh (1995)
Wrede, B., Fink, G.A., Sagerer, G.: An investigation of modelling aspects for rate-dependent speech recognition. In: Proc. of the INTERSPEECH, pp. 2527–2530 (2001)
Ban, S.M., Kim, H.S.: Speaking rate dependent multiple acoustic models using continuous frame rate normalization. In: Proc. of the Signal & Information Processing Association Annual Summit and Conference (APSIPA ASC), Asia-Pacific, pp. 1–4 (2012)
Nanjo, H., Kato, K., Kawahara, T.: Speaking rate dependent acoustic modeling for spontaneous lecture speech recognition. In: Proc. of the INTERSPEECH, pp. 2531–2534 (2001)
Chu, S.M., Povey, D.: Speaking rate adaptation using continuous frame rate normalization. In: Proc. of the IEEE International Conference in Acoustics Speech and Signal Processing (ICASSP), pp. 4306–4309 (2010)
Zhu, Q., Alwan, A.: On the use of variable frame rate analysis in speech recognition. In: Proc. of the 2000 IEEE International Conference in Acoustics Speech and Signal Processing (ICASSP 2000), pp. 1783–1786 (2000)
Benzeghiba, M., De Mori, R., Deroo, O., Dupont, S., Erbes, T., Jouvet, D., ... Wellekens, C. Automatic speech recognition and speech variability: A review. Speech Communication 49(10), 763–786 (2007)
Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.R., Jaitly, N., ... Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. Signal Processing Magazine 29(6), 82–97 (2012)
You, H., Zhu, Q., Alwan, A.: Entropy-based variable frame rate analysis of speech signals and its application to ASR. In: Proc. of the IEEE International Conference on In Acoustics, Speech, and Signal Processing – ICASSP 2004, vol. 1, pp. 549–552 (May 2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Tomashenko, N., Khokhlov, Y. (2014). Speaking Rate Estimation Based on Deep Neural Networks. In: Ronzhin, A., Potapova, R., Delic, V. (eds) Speech and Computer. SPECOM 2014. Lecture Notes in Computer Science(), vol 8773. Springer, Cham. https://doi.org/10.1007/978-3-319-11581-8_52
Download citation
DOI: https://doi.org/10.1007/978-3-319-11581-8_52
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11580-1
Online ISBN: 978-3-319-11581-8
eBook Packages: Computer ScienceComputer Science (R0)