Neuralecho: Hybrid of Full-Band and Sub-Band Recurrent Neural Network For Acoustic Echo Cancellation and Speech Enhancement
- Resource Type
- Conference
- Authors
- Yu, Meng; Xu, Yong; Zhang, Chunlei; Zhang, Shi-Xiong; Yu, Dong
- Source
- 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Automatic Speech Recognition and Understanding Workshop (ASRU), 2023 IEEE. :1-8 Dec, 2023
- Subject
- Signal Processing and Analysis
Training
Measurement
Recurrent neural networks
Echo cancellers
Conferences
Noise reduction
Speech enhancement
sub-band
full-band
echo cancellation
speech enhancement
- Language
This paper presents a hybrid of full-band and sub-band recurrent neural network (RNN) model, named NeuralEcho, to jointly solve echo and noise suppression. The full-band model part processes the signal’s entire frequency bands as a whole, while the sub-band model part divides the features into sub-bands and processes each sub-band separately. This approach allows the model to capture both the fine-grained local details of the sub-band processing and the global context of the full-band processing. The single-channel model is then generalized to accommodate a range of input channel numbers. Experimental results show that the hybrid model outperforms the conventional full-band models in terms of objective speech quality metrics and speech recognition accuracy. This suggests that the hybrid approach of full-band and sub-band processing can be a promising direction for future research in the field of speech enhancement.