Waveglow: A Flow-based Generative Network For Speech Synthesis

Abstract

In this paper we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms. WaveGlow combines insights from Glow and WaveNet in order to provide fast, efficient and high-quality audio synthesis, without the need for auto-regression. WaveGlow is implemented using only a single network, trained using only a single cost function: maximizing the likelihood of the training data, which makes the training procedure simple and stable. Our PyTorch implementation produces audio samples at a rate of more than 500 kHz on an NVIDIA V100 GPU. Mean Opinion Scores show that it delivers audio quality as good as the best publicly available WaveNet implementation. All code will be made publicly available online.

Stats

• citations566
• S2 citations—
• github stars0
• HF likes0
• heat score20.65
• arxiv keyprenger2018waveglow

Related papers

• Squeezewave: Extremely Lightweight Vocoders For On-device Speech Synthesis (2020)4.81
• Flowavenet : A Generative Flow For Raw Audio (2018)0.00
• Glow-wavegan 2: High-quality Zero-shot Text-to-speech Synthesis And Any-to-any Voice Conversion (2022)7.50
• Flowtron: An Autoregressive Flow-based Generative Network For Text-to-speech Synthesis (2020)5.91
• Hifi-gan: Generative Adversarial Networks For Efficient And High Fidelity Speech Synthesis (2020)0.00
• Glow-tts: A Generative Flow For Text-to-speech Via Monotonic Alignment Search (2020)0.00
• Waveform Generation For Text-to-speech Synthesis Using Pitch-synchronous Multi-scale Generative Adversarial Networks (2018)8.35
• Parallel Wavegan: A Fast Waveform Generation Model Based On Generative Adversarial Networks With Multi-resolution Spectrogram (2019)0.00