Corpus ID: 219792428

Boosting Objective Scores of Speech Enhancement Model through MetricGAN Post-Processing

  title={Boosting Objective Scores of Speech Enhancement Model through MetricGAN Post-Processing},
  author={S. Fu and Chien-Feng Liao and Tsun-An Hsieh and Kuo-Hsuan Hung and S. Wang and Cheng Yu and Heng-Cheng Kuo and Ryandhimas E. Zezario and Y. Li and Shang-Yi Chuang and Y. Lu and Y. Tsao},
  • S. Fu, Chien-Feng Liao, +9 authors Y. Tsao
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • The Transformer architecture has shown its superior ability than recurrent neural networks on many different natural language processing applications. Therefore, this study applies a modified Transformer on the speech enhancement task. Specifically, the positional encoding may not be necessary and hence is replaced by convolutional layers. To further improve PESQ scores of enhanced speech, the L_1 pre-trained Transformer is fine-tuned by MetricGAN framework. The proposed MetricGAN can be… CONTINUE READING
    1 Citations
    CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application
    • PDF


    Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
    • 349
    • PDF
    Multiple-target deep learning for LSTM-RNN based speech enhancement
    • 85
    • PDF
    T-GSA: Transformer with Gaussian-Weighted Self-Attention for Speech Enhancement
    • J. Kim, Mostafa El-Khamy, J. Lee
    • Computer Science, Engineering
    • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2020
    • 22
    • PDF
    Stable Training of Dnn for Speech Enhancement Based on Perceptually-Motivated Black-Box Cost Function
    • 7
    • Highly Influential
    • PDF
    A Regression Approach to Speech Enhancement Based on Deep Neural Networks
    • 716
    • PDF
    Weighted Speech Distortion Losses for Neural-Network-Based Real-Time Speech Enhancement
    • 24
    • PDF
    Speech enhancement based on deep denoising autoencoder
    • 490
    • PDF
    Speech Enhancement Using Self-Adaptation and Multi-Head Self-Attention
    • 18
    • PDF
    Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network
    • M. Soni, N. Shah, H. Patil
    • Computer Science
    • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2018
    • 60
    • PDF
    Learning With Learned Loss Function: Speech Enhancement With Quality-Net to Improve Perceptual Evaluation of Speech Quality
    • 9
    • PDF