paper-with-me

홈 › Papers

HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

2020-06-10 · Jiaqi Su, Zeyu Jin, Adam Finkelstein

Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a studio. We use an end-to-end feed-forward WaveNet architecture, trained with multi-scale adversarial discriminators in both the time domain and the time-frequency domain. It relies on the deep feature matching losses of the discriminators to improve the perceptual quality of enhanced speech. The proposed model generalizes well to new speakers, new speech content, and new environments. It significantly outperforms state-of-the-art baseline methods in both objective and subjective experiments.

📄 PDF Abstract BibTeX arXiv:2006.05694

Code (1)

rishikksh20/hifigan-denoiser pytorch

Tasks

DenoisingSpeech DereverberationSpeech Enhancement

Methods 이 논문이 사용한 방법론

Mixture of Logistic Distributions 설명 없음
Dilated Causal Convolution A Dilated Causal Convolution is a causal convolution where the filter is applied over an area larger than its length by…
WaveNet WaveNet is an audio generative model based on the PixelCNN architecture. In order to deal with long-range temporal dependencies…

Similar Papers 제목 키워드 기반

Simultaneous Denoising and Dereverberation Using Deep Embedding Features

2020-04-06 · Cunhang Fan, Jian-Hua Tao, Bin Liu, Jiangyan Yi 외

Monaural speech dereverberation is a very challenging task because no spatial cues can be used. When the additive noises exist, this task becomes more challenging. In this paper, we propose a joint training method for si…

ClusteringDeep ClusteringDenoisingSpeech Denoising+2

To Dereverb Or Not to Dereverb? Perceptual Studies On Real-Time Dereverberation Targets

2022-06-16 · Jean-Marc Valin, Ritwik Giri, Shrikant Venkataramani, Umut Isik 외

In real life, room effect, also known as room reverberation, and the present background noise degrade the quality of speech. Recently, deep learning-based speech enhancement approaches have shown a lot of promise and sur…

DenoisingSpeech Enhancement

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

2020-10-12 · NeurIPS 2020) 2020 10 · Jungil Kong, Jaehyeon Kim, Jaekyoung Bae

Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not …

CPUGPUSpeech Synthesis

D²Net: A Denoising and Dereverberation Network Based on Two-branch Encoder and Dual-path Transformer

2022-11-21 · APSIPA ASC 2022 11 · Liusong Wang, Wenbing Wei, Yadong Chen, and Ying Hu

The simultaneous denoising and dereverberation for single-channel mixture speech under the complicated acoustic environment is considered to be a challengeable task. In this paper, we propose a denoising and dereverberat…

DenoisingSpeech Enhancement

VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration

2022-04-12 · Haohe Liu, Xubo Liu, Qiuqiang Kong, Qiao Tian 외

Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on a single type of distortion, such as speech denoising or dereverberation. However, speech signals can be degraded by several …

Speech DenoisingSpeech EnhancementVocal Bursts Intensity Prediction