Skip to main content

Real-time speech enhancement with dynamic attention span

Chengyu Zheng (Communication University of China); Yuan Zhou (Microsoft Research Asia); Xiulian Peng (Microsoft Research Asia); Yuan Zhang (Communication University of China); Yan Lu (Microsoft Research Asia)

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

For real-time speech enhancement (SE) including noise suppression, dereverberation and acoustic echo cancellation, the time-variance of the audio signals becomes a severe challenge. The causality and memory usage limit that only the historical information can be used for the system to capture the time-variant characteristics. We propose to adaptively change the receptive field according to the input signal in deep neural network based SE model. Specifically, in an encoder-decoder framework, a dynamic attention span mechanism is introduced to all the attention modules for controlling the size of historical content used for processing the current frame. Experimental results verify that this dynamic mechanism can better track time-variant factors and capture speech-related characteristics, benefiting to both interference removing and speech quality retaining.

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