Metricgan: Generative Adversarial Networks Based Black-box Metric Scores Optimization For Speech Enhancement

Abstract

Adversarial loss in a conditional generative adversarial network (GAN) is not designed to directly optimize evaluation metrics of a target task, and thus, may not always guide the generator in a GAN to generate data with improved metric scores. To overcome this issue, we propose a novel MetricGAN approach with an aim to optimize the generator with respect to one or multiple evaluation metrics. Moreover, based on MetricGAN, the metric scores of the generated data can also be arbitrarily specified by users. We tested the proposed MetricGAN on a speech enhancement task, which is particularly suitable to verify the proposed approach because there are multiple metrics measuring different aspects of speech signals. Moreover, these metrics are generally complex and could not be fully optimized by Lp or conventional adversarial losses.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfu2019metricgan

Related papers

• Imetricgan: Intelligibility Enhancement For Speech-in-noise Using Generative Adversarial Network-based Metric Learning (2020)9.41
• Metricgan-u: Unsupervised Speech Enhancement/ Dereverberation Based Only On Noisy/ Reverberated Speech (2021)11.67
• Multi-metric Optimization Using Generative Adversarial Networks For Near-end Speech Intelligibility Enhancement (2021)8.60
• CMGAN: Conformer-based Metric-gan For Monaural Speech Enhancement (2022)14.80
• Boosting Objective Scores Of A Speech Enhancement Model By Metricgan Post-processing (2020)0.00
• CMGAN: Conformer-based Metric GAN For Speech Enhancement (2022)15.13
• Multi-cmgan+/+: Leveraging Multi-objective Speech Quality Metric Prediction For Speech Enhancement (2023)0.00
• On The Behavior Of Intrusive And Non-intrusive Speech Enhancement Metrics In Predictive And Generative Settings (2023)0.00