홈 › Papers

Parallel WaveNet: Fast High-Fidelity Speech Synthesis

2017-11-28 · ICML 2018 7 · Aaron van den Oord, Yazhe Li, Igor Babuschkin, Karen Simonyan, Oriol Vinyals, Koray Kavukcuoglu, George van den Driessche, Edward Lockhart, Luis C. Cobo, Florian Stimberg, Norman Casagrande, Dominik Grewe, Seb Noury, Sander Dieleman, Erich Elsen, Nal Kalchbrenner, Heiga Zen, Alex Graves, Helen King, Tom Walters, Dan Belov, Demis Hassabis

The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to today's massively parallel computers, and therefore hard to deploy in a real-time production setting. This paper introduces Probability Density Distillation, a new method for training a parallel feed-forward network from a trained WaveNet with no significant difference in quality. The resulting system is capable of generating high-fidelity speech samples at more than 20 times faster than real-time, and is deployed online by Google Assistant, including serving multiple English and Japanese voices.

📄 PDF Abstract BibTeX arXiv:1711.10433

Code (2)

HaiFengZeng/clari_wavenet_vocoder pytorch

PhilippeNguyen/keras_wavenet tf

Tasks

Speech Synthesis Vocal Bursts Intensity Prediction

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…

Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram

2019-10-25 · Ryuichi Yamamoto, Eunwoo Song, Jae-Min Kim

We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network. In the proposed method, a non-autoregressive WaveNet is trained by jointly op…

Generative Adversarial Network GPU Speech Synthesis text-to-speech+2

ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech

2018-07-19 · ICLR 2019 5 · Wei Ping, Kainan Peng, Jitong Chen

In this work, we propose a new solution for parallel wave generation by WaveNet. In contrast to parallel WaveNet (van den Oord et al., 2018), we distill a Gaussian inverse autoregressive flow from the autoregressive Wave…

Speech Synthesis text-to-speech Text to Speech

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 Reconstruction text-to-speech Text to Speech Vocal Bursts Intensity Prediction

Generative Adversarial Network based Speaker Adaptation for High Fidelity WaveNet Vocoder

2018-12-06 · Qiao Tian, Bing Yang, Jing Chen, Benlai Tang 외

Neural networks based vocoders, typically the WaveNet, have achieved spectacular performance for text-to-speech (TTS) in recent years. Although state-of-the-art parallel WaveNet has addressed the issue of real-time wavef…

Generative Adversarial Network text-to-speech Text to Speech Vocal Bursts Intensity Prediction

Parallel WaveNet conditioned on VAE latent vectors

2020-12-17 · Jonas Rohnke, Tom Merritt, Jaime Lorenzo-Trueba, Adam Gabrys 외

Recently the state-of-the-art text-to-speech synthesis systems have shifted to a two-model approach: a sequence-to-sequence model to predict a representation of speech (typically mel-spectrograms), followed by a 'neural …

Sentence Speech Synthesis text-to-speech Text to Speech+1