Improving the Quality of Automatic Speech Recognition in Trucks
In this paper we consider the problem of the DNN-HMM acoustic models training for automatic speech recognition systems on russian language in modern commercial trucks. The speech database for training and testing the ASR system was recorded in various models of trucks, operating under different conditions. The experiments on the test part of the speech database, show that acoustic models trained on the base of specifically modeled training speech database enable to improve the recognition quality in a moving truck from 35 % to 88 % compared to the acoustic models trained on a clean speech. Also a new topology of the neural network was proposed. It allows to reduce the computational costs significantly without loss of the recognition accuracy.
KeywordsASR DNN MFCC CMVN Multi-bottleneck Database Trucks
This work was financially supported by the Ministry of Education and Science of the Russian Federation, Contract 14.575.21.0033 (ID RFMEFI57514X0033).
- 1.Prudnikov, A., Korenevsky, M., Aleinik, S.: Adaptive beamforming and adaptive training of DNN acoustic models for enhanced multichannel noisy speech recognition. In: IEEE Automatic Speech Recognition and Understanding Workshop, pp. 401–408. IEEE Press, Scottsdale (2015)Google Scholar
- 2.Levin, K., Ponomareva, I., Bulusheva, A., Chernykh, G., Medennikov, I., Merkin, N., Prudnikov, A., Tomashenko, N.: Automated closed captioning for Russian live broadcasting. In: 16th Annual Conference of the International Speech Communication Association (Interspeech), Singapore, pp. 1438–1442 (2014)Google Scholar
- 3.Siemund, R., Hoge, H., Kunzmann, S., Marasek, K.: SPEECON speech data for consumer devices. In: Second International Conference on Language Resources and Evaluation, Athens, vol. II, pp. 883–886 (2000)Google Scholar
- 4.Arlazarov, V.L., Bogdanov, D.S., Krivnova, O.F., Podrabinovitch, A.Y.: Creation of Russian speech databases: design, processing, development tools. In: SPECOM 2004, Saint-Petersburg, Russia, pp. 650–656 (2004)Google Scholar
- 5.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 Workshop on Automatic Speech Recognition and Understanding, ASRU 2011 (2011)Google Scholar
- 6.Kim, C., Stern, R.: Power-normalized cepstral coefficients (PNCC) for robust speech recognition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 4101–4104 (2012)Google Scholar
- 8.European Telecommunications Standards Institute, Speech Processing, Transmission and Quality Aspects (STQ); Distributed Speech Recognition; Advanced Front-end Feature Extraction Algorithm; Compression Algorithms, es 202 050, Rev. 1.1.5 edn. (2007)Google Scholar
- 11.Seide, F., Li, G., Chen, X., Yu, D.: Feature engineering in context-dependent deep neural networks for conversational speech transcription. In: 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 24–29. IEEE (2011)Google Scholar