Skip to main content

CONVOLUTIONAL RECURRENT METRICGAN WITH SPECTRAL DIMENSION COMPRESSION FOR FULL-BAND SPEECH ENHANCEMENT

Zhongshu Hou (Nanjing University); Qinwen Hu (Nanjing University); Tianchi Sun (Nanjing University); Yuxiang Hu (Horizon Robotics); Changbao Zhu (Horizon Robotics); Kai Chen (Nanjing University)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
10 Jun 2023

MetricGAN and its variations have been proven to be an effective wide-band speech enhancement model. In this paper, we expand it to full-band enhancement by combining our recently proposed learnable spectral dimension compression mapping strategy. The encoder-decoder structure with a time-frequency convolutional recurrent network is utilized as the generator. The proposed model is submitted to the ICASSP Signal Processing Grand Challenge: DNS-5 Challenge (2023). Without using the enrollment speech, it obtains a final score of 0.548 on Track-1 and 0.559 on Track-2.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00