paper-with-me

Papers

MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

2021-04-08 · Szu-Wei Fu, Cheng Yu, Tsun-An Hsieh, Peter Plantinga, Mirco Ravanelli, Xugang Lu, Yu Tsao

The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception can hence serve as a bridge to reduce the gap. Our previously proposed MetricGAN was designed to optimize objective metrics by connecting the metric with a discriminator. Because only the scores of the target evaluation functions are needed during training, the metrics can even be non-differentiable. In this study, we propose a MetricGAN+ in which three training techniques incorporating domain-knowledge of speech processing are proposed. With these techniques, experimental results on the VoiceBank-DEMAND dataset show that MetricGAN+ can increase PESQ score by 0.3 compared to the previous MetricGAN and achieve state-of-the-art results (PESQ score = 3.15).

📄 PDF Abstract BibTeX arXiv:2104.03538

Code (3)

speechbrain/speechbrain/tree/develop/recipes/Voicebank/enhance/MetricGAN 공식 구현 pytorch
JasonSWFu/MetricGAN
wooseok-shin/MetricGAN-plus-pytorch pytorch

Tasks

Speech Enhancement

Similar Papers 제목 키워드 기반

MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech Enhancement

2023-07-24 · ICML 2023 7 · WooSeok Shin, Byung Hoon Lee, Jin Sob Kim, Hyun Joon Park 외

In speech enhancement, MetricGAN-based approaches reduce the discrepancy between the $L_p$ loss and evaluation metrics by utilizing a non-differentiable evaluation metric as the objective function. However, optimizing mu…

Knowledge DistillationSpeech Enhancement

MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement

2019-05-13 · Szu-Wei Fu, Chien-Feng Liao, Yu Tsao, Shou-De Lin

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…

Generative Adversarial NetworkSpeech Enhancement

MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech

2021-10-12 · Szu-Wei Fu, Cheng Yu, Kuo-Hsuan Hung, Mirco Ravanelli 외

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…

Speech Enhancement

Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing

2020-06-18 · Szu-Wei Fu, Chien-Feng Liao, Tsun-An Hsieh, Kuo-Hsuan Hung 외

The Transformer architecture has demonstrated a superior ability compared to recurrent neural networks in many different natural language processing applications. Therefore, our study applies a modified Transformer in a …

Speech Enhancement

MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data

2022-03-23 · George Close, Thomas Hain, Stefan Goetze

Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically motivated speech perception metrics as par…

Speech Enhancement