Self-Attending RNN for Speech Enhancement to Improve Cross-Corpus Generalization

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

Self-Attending RNN for Speech Enhancement to Improve Cross-Corpus Generalization

By: 
Ashutosh Pandey; DeLiang Wang

Deep neural networks (DNNs) represent the mainstream methodology for supervised speech enhancement, primarily due to their capability to model complex functions using hierarchical representations. However, a recent study revealed that DNNs trained on a single corpus fail to generalize to untrained corpora, especially in low signal-to-noise ratio (SNR) conditions. Developing a noise, speaker, and corpus independent speech enhancement algorithm is essential for real-world applications. In this study, we propose a self-attending recurrent neural network, or attentive recurrent network (ARN), for time-domain speech enhancement to improve cross-corpus generalization. ARN comprises of recurrent neural networks (RNNs) augmented with self-attention blocks and feedforward blocks. We evaluate ARN on different corpora with nonstationary noises in low SNR conditions. Experimental results demonstrate that ARN substantially outperforms competitive approaches to time-domain speech enhancement, such as RNNs and dual-path ARNs. Additionally, we report an important finding that the two popular approaches to speech enhancement: complex spectral mapping and time-domain enhancement, obtain similar results for RNN and ARN with large-scale training. We also provide a challenging subset of the test set used in this study for evaluating future algorithms and facilitating direct comparisons.

SPS on Twitter

  • CALL FOR PROPOSALS: Now seeking proposals for the 2024 IEEE International Workshop on Machine Learning for Signal P… https://t.co/l7V1bF2qhT
  • The DEGAS Webinar Series continues on Thursday, 19 May when Dr. Usman A. Khan presents "Distributed stochastic non-… https://t.co/AbfwVL0Yne
  • The IEEE Journal of Selected Topics in Signal Processing is now accepting submissions for a Special Issue on Signal… https://t.co/PbuzgYLigt
  • RT : New graduates transitioning to the next stage of their career often have several questions. In this video, I share… https://t.co/WA4aRlKNRn
  • DEADLINE EXTENDED: The IEEE Journal of Selected Topics in Signal Processing is accepting papers for a Special Issue… https://t.co/4RCWojWXO0

SPS Videos


Signal Processing in Home Assistants

 


Multimedia Forensics


Careers in Signal Processing             

 


Under the Radar