Precision Scaling of Neural Networks for Efficient Audio Processing

Preprint English OPEN
Ko, Jong Hwan ; Fromm, Josh ; Philipose, Matthai ; Tashev, Ivan ; Zarar, Shuayb (2017)
  • Subject: Electrical Engineering and Systems Science - Audio and Speech Processing | Computer Science - Sound

While deep neural networks have shown powerful performance in many audio applications, their large computation and memory demand has been a challenge for real-time processing. In this paper, we study the impact of scaling the precision of neural networks on the performance of two common audio processing tasks, namely, voice-activity detection and single-channel speech enhancement. We determine the optimal pair of weight/neuron bit precision by exploring its impact on both the performance and processing time. Through experiments conducted with real user data, we demonstrate that deep neural networks that use lower bit precision significantly reduce the processing time (up to 30x). However, their performance impact is low (< 3.14%) only in the case of classification tasks such as those present in voice activity detection.
  • References (14)
    14 references, page 1 of 2

    [1] Xiao-lei Zhang and Deliang Wang. Boosting Contextual Information for Deep Neural Network Based Voice Activity Detection. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 24(2):252-264, 2016.

    [2] Ivan Tashev and Seyedmahdad Mirsamadi. DNN-based Causal Voice Activity Detector. In Information Theory and Applications Workshop, 2016.

    [3] Yong Xu, Jun Du, Li-Rong Dai, and Chin-Hui Lee. An Experimental Study on Speech Enhancement Based on Deep Neural Networks. IEEE Signal Processing Letters, 21(1):65-68, 2014.

    [4] Xiao-lei Zhang and Ji Wu. Deep Belief Networks Based Voice Activity Detection. IEEE Transactions on Audio, Speech, and Language Processing, 21(4):697-710, 2013.

    [5] J. H. Ko, D. Kim, T. Na, J. Kung, and S. Mukhopadhyay. Adaptive weight compression for memory-efficient neural networks. Design, Automation Test in Europe Conference Exhibition (DATE), 2017, pages 199-204, March 2017.

    [6] A. Agrawal et al. An introduction to computational networks and the computational network toolkit. Microsoft Technical Report MSR-TR-2014-112, 2014.

    [7] Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. Journal of Machine Learning Research, 1:1-48, 2000.

    [8] Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, and Jian Cheng. Quantized Convolutional Neural Networks for Mobile Devices. Arxiv 2016, page 11, 2016.

    [9] T. Na and S. Mukhopadhyay. Speeding Up Convolutional Neural Network Training with Dynamic Precision Scaling and Flexible Multiplier-Accumulator. ISLPED 2016.


  • Metrics
    No metrics available
Share - Bookmark