• Corpus ID: 239016711

Controllable Multichannel Speech Dereverberation based on Deep Neural Networks

  title={Controllable Multichannel Speech Dereverberation based on Deep Neural Networks},
  author={Ziteng Wang and Yueyue Na and Biao Tian and Qiang Fu},
  • Ziteng Wang, Yueyue Na, +1 author Qiang Fu
  • Published 16 October 2021
  • Computer Science, Engineering
  • ArXiv
Neural network based speech dereverberation has achieved promising results in recent studies. Nevertheless, many are focused on recovery of only the direct path sound and early reflections, which could be beneficial to speech perception, are discarded. The performance of a model trained to recover clean speech degrades when evaluated on early reverberation targets, and vice versa. This paper proposes a novel deep neural network based multichannel speech dereverberation algorithm, in which the… 

Figures and Tables from this paper


Deep Learning Based Target Cancellation for Speech Dereverberation
These models show excellent speech dereverberation and recognition performance on the test set of the REVERB challenge, consistently better than single- and multi-channel weighted prediction error (WPE) algorithms.
Speech Dereverberation Using Fully Convolutional Networks
This paper investigates the applicability of fully convolutional networks to enhance the speech signal represented by short-time Fourier transform images and presents two variations: a “U-Net” which is an encoder-decoder network with skip connections and a generative adversarial network (GAN) with U-Net as generator, which yields a more intuitive cost function for training.
Multi-Microphone Complex Spectral Mapping for Speech Dereverberation
  • Zhong-Qiu Wang, Deliang Wang
  • Computer Science, Engineering
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2020
Experimental results on multi-channel speech dereverberation demonstrate the effectiveness of the proposed approach and the integration of multi-microphone complex spectral mapping with beamforming and post-filtering is investigated.
A Reverberation-Time-Aware Approach to Speech Dereverberation Based on Deep Neural Networks
The proposed framework outperforms the conventional DNNs without taking the reverberation time into account, while achieving a performance only slightly worse than the oracle cases with known reverberation times even for extremely weak and severe reverberant conditions.
Two-Stage Deep Learning for Noisy-Reverberant Speech Enhancement
This work proposes a two-stage strategy to enhance corrupted speech, where denoising and dereverberation are conducted sequentially using deep neural networks, and designs a new objective function that incorporates clean phase during model training to better estimate spectral magnitudes.
Learning Spectral Mapping for Speech Dereverberation and Denoising
Deep neural networks are trained to directly learn a spectral mapping from the magnitude spectrogram of corrupted speech to that of clean speech, which substantially attenuates the distortion caused by reverberation, as well as background noise, and is conceptually simple.
Late Reverberation Suppression Using Recurrent Neural Networks with Long Short-Term Memory
A supervised speech dereverberation algorithm that models late reverberation using a recurrent neural network (RNN) with long short-term memory (LSTM) to take advantage of LSTM's ability to capture a long history can be effectively removed by the proposed approach.
Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising
This paper performs dereverberation and denoising using supervised learning with a deep neural network and defines the complex ideal ratio mask so that direct speech results after the mask is applied to reverberant and noisy speech.
Neural Network-Based Spectrum Estimation for Online WPE Dereverberation
A novel speech dereverberation framework that utilizes deep neural network (DNN)-based spectrum estimation to construct linear inverse filters is proposed that outperforms the conventional WPE, and improves the ASR performance in real noisy reverberant environments in both single-channel and multichannel cases.
A Simultaneous Denoising and Dereverberation Framework with Target Decoupling
An integrated framework to address simultaneous denoising and dereverberation under complicated scenario environments is proposed and adopts a chain optimization strategy and designs four sub-stages accordingly.