Metricgan-u: Unsupervised Speech Enhancement/ Dereverberation Based Only On Noisy/ Reverberated Speech

Abstract

Most of the deep learning-based speech enhancement models are learned in a supervised manner, which implies that pairs of noisy and clean speech are required during training. Consequently, several noisy speeches recorded in daily life cannot be used to train the model. Although certain unsupervised learning frameworks have also been proposed to solve the pair constraint, they still require clean speech or noise for training. Therefore, in this paper, we propose MetricGAN-U, which stands for MetricGAN-unsupervised, to further release the constraint from conventional unsupervised learning. In MetricGAN-U, only noisy speech is required to train the model by optimizing non-intrusive speech quality metrics. The experimental results verified that MetricGAN-U outperforms baselines in both objective and subjective metrics.

Stats

• citations35
• S2 citations—
• github stars0
• HF likes0
• heat score11.67
• arxiv keyfu2021metricgan

Related papers

• Imetricgan: Intelligibility Enhancement For Speech-in-noise Using Generative Adversarial Network-based Metric Learning (2020)9.41
• Metricgan: Generative Adversarial Networks Based Black-box Metric Scores Optimization For Speech Enhancement (2019)0.00
• CMGAN: Conformer-based Metric-gan For Monaural Speech Enhancement (2022)14.80
• Unetgan: A Robust Speech Enhancement Approach In Time Domain For Extremely Low Signal-to-noise Ratio Condition (2020)11.49
• Multi-metric Optimization Using Generative Adversarial Networks For Near-end Speech Intelligibility Enhancement (2021)8.60
• Multi-cmgan+/+: Leveraging Multi-objective Speech Quality Metric Prediction For Speech Enhancement (2023)0.00
• A Comparative Evaluation Of Deep Learning Models For Speech Enhancement In Real-world Noisy Environments (2025)0.00
• Unsupervised Speech Enhancement With Deep Dynamical Generative Speech And Noise Models (2023)0.00