paper-with-me

Papers

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-spectograms. We propose that it is possible to transfer the MelGAN's [3] robustness in learning speech features to speech enhancement and noise reduction domain without any model modification tasks. Our proposed method generalizes over multi-speaker speech dataset and is able to robustly handle unseen background noises during the inference. Also, we show that by increasing the batch size for this particular approach not only yields better speech results, but generalizes over multi-speaker dataset easily and leads to faster convergence. Additionally, it outperforms previous state of the art GAN approach for speech enhancement SEGAN [5] in two domains: 1. quality ; 2. speed. Proposed method runs at more than 100x faster than realtime on GPU and more than 2x faster than real time on CPU without any hardware optimization tasks, right at the speed of MelGAN [3].

📄 PDF Abstract BibTeX arXiv:2006.07637

Code (0)

등록된 구현이 없습니다.

Tasks

CPUGPUSpeech EnhancementSpeech Synthesis

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
Tanh Activation 설명 없음
GAN Hinge Loss The GAN Hinge Loss is a hinge loss based loss function for [generative adversarial…
Weight Normalization Weight Normalization is a normalization method for training neural networks. It is inspired by batch normalization,…
Average Pooling 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domains

2020-11-19 · Won Jang, Dan Lim, Jaesam Yoon

We propose Universal MelGAN, a vocoder that synthesizes high-fidelity speech in multiple domains. To preserve sound quality when the MelGAN-based structure is trained with a dataset of hundreds of speakers, we added mult…

text-to-speechText to Speech

MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms

2019-10-08 · Marco Pasini

Traditional voice conversion methods rely on parallel recordings of multiple speakers pronouncing the same sentences. For real-world applications however, parallel data is rarely available. We propose MelGAN-VC, a voice …

Generative Adversarial NetworkMusic Style TransferStyle TransferTranslation+1

StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization

2020-11-03 · Ahmed Mustafa, Nicola Pia, Guillaume Fuchs

In recent years, neural vocoders have surpassed classical speech generation approaches in naturalness and perceptual quality of the synthesized speech. Computationally heavy models like WaveNet and WaveGlow achieve best …

Spectral Reconstructiontext-to-speechText to SpeechVocal Bursts Intensity Prediction

Relational Data Selection for Data Augmentation of Speaker-dependent Multi-band MelGAN Vocoder

2021-06-10 · Yi-Chiao Wu, Cheng-Hung Hu, Hung-Shin Lee, Yu-Huai Peng 외

Nowadays, neural vocoders can generate very high-fidelity speech when a bunch of training data is available. Although a speaker-dependent (SD) vocoder usually outperforms a speaker-independent (SI) vocoder, it is impract…

Data AugmentationSpeaker Verification

The Potential of Neural Speech Synthesis-based Data Augmentation for Personalized Speech Enhancement

2022-11-14 · Anastasia Kuznetsova, Aswin Sivaraman, Minje Kim

With the advances in deep learning, speech enhancement systems benefited from large neural network architectures and achieved state-of-the-art quality. However, speaker-agnostic methods are not always desirable, both in …

Data AugmentationSpeech EnhancementSpeech Synthesis