Enhancing Voice Assistant Accuracy through Multi-task Learning

  • Authors

    • Dr. Rakesh Chandra Associate Professor University of Calcutta, India. Author

    DOI:

    https://doi.org/10.67228/3142788X/IJMLPA-2019PII7V4Q

    Published 07-04-2019

  • Voice Assistants, Multi-Task Learning (Mtl), Speech Recognition, Natural Language Understanding, Contextual Interpretation, Accuracy Enhancement, Machine Learning, Artificial Intelligence, User Interaction, Noise Robustness

    Issue

    Vol. 2 No. 2 (2019)

    Section

    Articles

    How to Cite

    [1]
    R. Chandra, “Enhancing Voice Assistant Accuracy through Multi-task Learning”, IJMLPA, vol. 2, no. 2, pp. 01–08, Jul. 2019, doi: 10.67228/3142788X/IJMLPA-2019PII7V4Q.

  • Abstract

    Voice assistants have become integral in many daily tasks, yet their accuracy in handling complex commands and diverse environments remains a challenge. This paper explores the potential of multi-task learning (MTL) as a method to enhance the accuracy of voice assistants by simultaneously training multiple related tasks such as speech recognition, natural language understanding, and contextual interpretation. The research proposes a multi-task learning model that shares knowledge between tasks, allowing for improved generalization across various input conditions. Experimental results demonstrate that MTL improves accuracy and robustness in noisy environments, as well as in diverse accents and linguistic variations. The findings suggest that integrating multi-task learning into voice assistant systems can lead to significant improvements in both performance and user satisfaction.

  • References

    [1] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS), 30.

    [2] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, 4171-4186.

    [3] Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527-1554.

    [4] Zhang, Y., & Chen, X. (2019). Deep learning for voice assistants: A review of approaches and applications. IEEE Access, 7, 128568-128583.

    [5] Collobert, R., & Weston, J. (2008). A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of ICML, 160-167.

    [6] Ruder, S., Peters, M. E., Swayamdipta, S., & Søgaard, A. (2019). Transfer learning in natural language processing. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 15-38.

    [7] Sperber, M., & Peddinti, V. (2018). Improving speech recognition using multi-task learning: A review. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 5148-5152.

    [8] Luong, M. T., Pham, H., & Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. In Proceedings of EMNLP, 1412-1421.

    [9] Hannun, A., Lee, K., Qian, Y., et al. (2014). Deep speech: Scaling up end-to-end speech recognition. arXiv:1412.5567.

    [10] Xiong, W., Hu, X., & Yan, X. (2016). Deep learning for speech recognition: From feature extraction to end-to-end models. IEEE Transactions on Neural Networks and Learning Systems, 27(9), 1862-1875.

    [11] Zhou, X., & Chen, X. (2019). Multi-task learning in neural networks: A survey. IEEE Transactions on Knowledge and Data Engineering, 31(6), 1058-1072.

    [12] Li, Y., & Liu, W. (2018). Enhancing spoken language understanding with multi-task learning. In Proceedings of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH), 2351-2355.

    [13] Rastegar, H., & Tabrizi, A. (2019). Exploring multi-task learning for speech and language processing. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 7059-7063.

    [14] Chen, Y., & Sun, M. (2018). Multitask deep neural networks for context-aware conversational agents. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 4571-4578.

  • Downloads