Adversarial Feature-mapping For Speech Enhancement

Abstract

Feature-mapping with deep neural networks is commonly used for single-channel speech enhancement, in which a feature-mapping network directly transforms the noisy features to the corresponding enhanced ones and is trained to minimize the mean square errors between the enhanced and clean features. In this paper, we propose an adversarial feature-mapping (AFM) method for speech enhancement which advances the feature-mapping approach with adversarial learning. An additional discriminator network is introduced to distinguish the enhanced features from the real clean ones. The two networks are jointly optimized to minimize the feature-mapping loss and simultaneously mini-maximize the discrimination loss. The distribution of the enhanced features is further pushed towards that of the clean features through this adversarial multi-task training. To achieve better performance on ASR task, senone-aware (SA) AFM is further proposed in which an acoustic model network is jointly trained with the fe

Stats

• citations24
• S2 citations—
• github stars0
• HF likes0
• heat score10.48
• arxiv keymeng2018adversarial

Related papers

• Boosting Noise Robustness Of Acoustic Model Via Deep Adversarial Training (2018)9.23
• Unpaired Speech Enhancement By Acoustic And Adversarial Supervision For Speech Recognition (2018)10.21
• Single Channel Far Field Feature Enhancement For Speaker Verification In The Wild (2020)0.00
• Enhancing And Adversarial: Improve ASR With Speaker Labels (2022)5.24
• On The Use Of Audio Fingerprinting Features For Speech Enhancement With Generative Adversarial Network (2020)0.00
• Adversarial Speaker Adaptation (2019)10.21
• Superm2m: Supervised And Mixture-to-mixture Co-learning For Speech Enhancement And Noise-robust ASR (2024)5.24
• Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement (2022)0.00