Abstract
Recurrent neural networks (RNNs) have achieved remarkable improvements in acoustic modeling recently. However, the potential of RNNs have not been utilized for modeling Urdu acoustics. The connectionist temporal classification and attention based RNNs are suffered due to the unavailability of lexicon and computational cost of training, respectively. Therefore, we explored contemporary long short-term memory and gated recurrent neural networks Urdu acoustic modeling. The efficacies of plain, deep, bidirectional and deep-directional network architectures are evaluated empirically. Results indicate that deep-directional has an advantage over the other architectures. A word error rate of 20% was achieved on a hundred words dataset of twenty speakers. It shows 15% improvement over the baseline single-layer LSTMs. It has been observed that two-layer architectures can improve performance over single-layer, however the performance is degraded with further layers. LSTM architectures were compared with gated recurrent unit (GRU) based architectures and it was found that LSTM has an advantage over GRU.
Similar content being viewed by others
Notes
The sequence processing using neural networks is usually performed by operating over a context window at the first layer. We have not considered context window in this section for notational convenience.
Biases are omitted throughout the paper for simplicity.
“Center for Language Engineering” [Online]. Available: http://www.cle.org.pk.
“Python_speech_features toolkit” [Online]. Available: https://python-speech-features.readthedocs.io/en/latest/.
“Colaboratory”, Available: https://colab.research.google.com/notebooks/welcome.ipynb#recent=true.
References
Ahad, A., Fayyaz, A., & Mehmood, T. (2002). Speech recognition using multilayer perceptron. In Proceedings of IEEE students conference (Vol. 1, pp 103–109).
Ali, H., Ahmad, N., & Hafeez, A. (2016). Urdu speech corpus and preliminary results on speech recognition. In International conference on engineering applications of neural networks (pp 317–325). New York: Springer.
Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G., & Chen, J. (2016). Deep speech 2: End-to-end speech recognition in English and Mandarin. In International conference on machine Learning (pp 173–182).
Ashraf, J., Iqbal, N., Khattak, N. S., & Zaidi, A. M. (2010). Speaker independent Urdu speech recognition using HMM. In 7th IEEE international conference on informatics and systems (INFOS) (pp 1–5).
Azam, S. M., Mansoor, Z. A., Mughal, M. S., & Mohsin, S. (2007). Urdu spoken digits recognition using classified MFCC and backpropgation neural network. In IEEE conference on computer graphics, imaging and visualisation (pp 414–418).
Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., & Bengio, Y. (2016). End-to-end attention-based large vocabulary speech recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4945–4949). IEEE.
Chan, W., Jaitly, N., Le, Q., & Vinyals, O. (2016). Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4960–4964). IEEE.
Chan, W., & Lane, I. (2015), Deep recurrent neural networks for acoustic modelling. arXiv Preprint arXiv:1504.01482.
Chiu, C. C., Sainath, T. N., Wu, Y., Prabhavalkar, R., Nguyen, P., Chen, Z., & Jaitly, N. (2017). State-of-the-art speech recognition with sequence-to-sequence models. arXiv Preprint arXiv:1712.01769.
Chollet, F. (2015). Keras.
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv Preprint arXiv:1412.3555.
Graves, A., & Jaitly, N. (2014). Towards end-to-end speech recognition with recurrent neural networks. In Proceedings of the 31st international conference on machine learning (ICML-14) (pp 1764–1772).
Graves, A., Mohamed, A. R., & Hinton, G. (2013a). Speech recognition with deep recurrent neural networks. In IEEE international conference on acoustics, speech and signal processing (pp 6645–6649).
Graves, A., Jaitly, N., & Mohamed, A. R. (2013b). Hybrid speech recognition with deep bidirectional LSTM. In IEEE workshop on automatic speech recognition and understanding (ASRU), pp 273–278.
Graves, A., & Schmidhuber, J. (2009). Offline handwriting recognition with multidimensional recurrent neural networks. In Advances in neural information processing systems (pp 545–552).
Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. In IEEE transactions on neural networks and learning systems.
Hannun, A., Case, C., Casper, J., Catanzaro, B., Diamos, G., Elsen, E., Prenger, R., Satheesh, S., Sengupta, S., Coates, A., & Ng, A. Y. (2014). Deep speech: Scaling up end-to-end speech recognition. arXiv Preprint arXiv:1412.5567.
Hasnain, S. K., & Awan, M. S. (2008). Recognizing spoken Urdu numbers using Fourier descriptor and neural networks with Matlab. In Second international IEEE conference on electrical engineering (pp 1–6).
Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A. R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T. N., & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82–97.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
Juang, B. H., & Rabiner, L. R. (1991). Hidden Markov models for speech recognition. Technometrics, 33(3), 251–272.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp 1097–1105).
Lipton, Z. C., Berkowitz, J., & Elkan, C. (2015). A critical review of recurrent neural networks for sequence learning. arXiv Preprint arXiv:1506.00019.
Mikolov, T., Karafiát, M., Burget, L., Cernocký, J., & Khudanpur, S. (2010). Recurrent neural network based language model. Interspeech, 2, 3.
Pascanu, R., Gulcehre, C., Cho, K., & Bengio, Y. (2013). How to construct deep recurrent neural networks. arXiv Preprint arXiv:1312.6026.
Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training recurrent neural networks. In International conference on machine learning (pp 1310–1318).
Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257–286.
Rao, K., & Sak, H. (2017). Multi-accent speech recognition with hierarchical grapheme based models. In 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), (pp. 4815–4819). IEEE.
Sak, H., Senior, A., & Beaufays, F. (2014). Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In Fifteenth Annual Conference of the International Speech Communication Association.
Sak, H., Senior, A., Rao, K., & Beaufays, F. (2015). Fast and accurate recurrent neural network acoustic models for speech recognition. arXiv Preprint arXiv:1507.06947.
Sarfraz, H., Hussain, S., Bokhari, R., Raza, A. A., Ullah, I., Sarfraz, Z., Pervez, S., Mustafa, A., Javed, I., & Parveen, R. (2010). Large vocabulary continuous speech recognition for Urdu. In Proceedings of the 8th ACM international conference on frontiers of information technology (p 1).
Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681.
Sutskever, I., Vinyals, O., & Le, Q. V. (2014), Sequence to sequence learning with neural networks. In Advances in neural information processing systems (pp 3104–3112).
Williams, R. J., & Peng, J. (1990). An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural computation, 2(4), 490–501.
Yu, D., & Li, J. (2017). Recent progresses in deep learning based acoustic models. IEEE/CAA Journal of Automatica Sinica, 4(3), 396–409.
Zweig, G., Yu, C., Stolcke, D. J., A. (2017). Advances in all-neural speech recognition. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4805–4809). IEEE.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zia, T., Zahid, U. Long short-term memory recurrent neural network architectures for Urdu acoustic modeling. Int J Speech Technol 22, 21–30 (2019). https://doi.org/10.1007/s10772-018-09573-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10772-018-09573-7