Echo Cancelation and Noise Suppression by Training a Dual-Stream Recurrent Network with a Mixture of Training Targets
- Resource Type
- Conference
- Authors
- Alishahi, Fatemeh; Cao, Yin; Kim, Youngkoen; Mohammad, Asif
- Source
- 2022 International Workshop on Acoustic Signal Enhancement (IWAENC) Acoustic Signal Enhancement (IWAENC), 2022 International Workshop on. :1-5 Sep, 2022
- Subject
- Computing and Processing
Signal Processing and Analysis
Training
Measurement
Echo cancellers
Noise reduction
Signal processing algorithms
Speech enhancement
Feature extraction
Supervised speech enhancement
deep neural network
recurrent neural networks
training targets
- Language
Nonlinear echo in presence of background noise can degrade the performance of digital signal processing algorithms. Deep neural networks with their ability to model complex nonlinear functions can potentially address this issue. In this paper, a deep and causal neural network based on dual streaming of the near-end microphone and far-end speech signals is employed to leverage the real-time nonlinear echo cancellation and noise suppression. The extracted features of two streams are coupled into a shared neural network for joint echo and noise cancellation. The training target is a mixture of spectral mapping and masking-based targets which are gated through a feedforward neural network. The model is evaluated in terms of both signal-level and perception-level metrics for different scenarios with a range of SI-SDR as low as −25 dB. Furthermore, the effect of mixing of training targets is assessed by evaluating different models.