paper-with-me

Papers

Real Time Speech Enhancement in the Waveform Domain

2020-06-23 · Alexandre Defossez, Gabriel Synnaeve, Yossi Adi

We present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities. We perform evaluations on several standard benchmarks, both using objective metrics and human judgements. The proposed model matches state-of-the-art performance of both causal and non causal methods while working directly on the raw waveform.

📄 PDF Abstract BibTeX arXiv:2006.12847

Code (3)

facebookresearch/denoiser 공식 구현 pytorch
jonashaag/paperswithcode-speech-enhancement-audiosamples/tree/master/Real%20Time%20Speech%20Enhancement%20in%20the%20Waveform%20Domain
yunyangzeng/taploss pytorch

Tasks

CPUData AugmentationDecoderSpeech Enhancement

Similar Papers 제목 키워드 기반

A non-causal FFTNet architecture for speech enhancement

2020-06-08 · Muhammed PV Shifas, Nagaraj Adiga, Vassilis Tsiaras, Yannis Stylianou

In this paper, we suggest a new parallel, non-causal and shallow waveform domain architecture for speech enhancement based on FFTNet, a neural network for generating high quality audio waveform. In contrast to other wave…

Speech Enhancement

SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement

2020-06-13 · Luka Chkhetiani, Levan Bejanidze

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectog…

CPUGPUSpeech EnhancementSpeech Synthesis

Multichannel Speech Enhancement by Raw Waveform-mapping using Fully Convolutional Networks

2019-09-26 · Chang-Le Liu, Sze-Wei Fu, You-Jin Li, Jen-Wei Huang 외

In recent years, waveform-mapping-based speech enhancement (SE) methods have garnered significant attention. These methods generally use a deep learning model to directly process and reconstruct speech waveforms. Because…

DenoisingSpeech Enhancement

A Neural Denoising Vocoder for Clean Waveform Generation from Noisy Mel-Spectrogram based on Amplitude and Phase Predictions

2024-11-19 · Hui-Peng Du, Ye-Xin Lu, Yang Ai, Zhen-Hua Ling

This paper proposes a novel neural denoising vocoder that can generate clean speech waveforms from noisy mel-spectrograms. The proposed neural denoising vocoder consists of two components, i.e., a spectrum predictor and …

DenoisingSpeech Enhancement

Time-domain Speech Enhancement with Generative Adversarial Learning

2021-03-30 · Feiyang Xiao, Jian Guan, Qiuqiang Kong, Wenwu Wang

Speech enhancement aims to obtain speech signals with high intelligibility and quality from noisy speech. Recent work has demonstrated the excellent performance of time-domain deep learning methods, such as Conv-TasNet. …

Generative Adversarial NetworkSpeech Enhancement