Fbwave: Efficient And Scalable Neural Vocoders For Streaming Text-to-speech On The Edge
2020 · Bichen Wu, Qing He, Peizhao Zhang, et al.
Abstract
Nowadays more and more applications can benefit from edge-based text-to-speech (TTS). However, most existing TTS models are too computationally expensive and are not flexible enough to be deployed on the diverse variety of edge devices with their equally diverse computational capacities. To address this, we propose FBWave, a family of efficient and scalable neural vocoders that can achieve optimal performance-efficiency trade-offs for different edge devices. FBWave is a hybrid flow-based generative model that combines the advantages of autoregressive and non-autoregressive models. It produces high quality audio and supports streaming during inference while remaining highly computationally efficient. Our experiments show that FBWave can achieve similar audio quality to WaveRNN while reducing MACs by 40x. More efficient variants of FBWave can achieve up to 109x fewer MACs while still delivering acceptable audio quality. Audio demos are available at https://bichenwu09.github.io/vocoder_de
Authors
(none)
Tags
Stats
Related papers
- Squeezewave: Extremely Lightweight Vocoders For On-device Speech Synthesis (2020)4.81
- Featherwave: An Efficient High-fidelity Neural Vocoder With Multi-band Linear Prediction (2020)8.35
- Flowvocoder: A Small Footprint Neural Vocoder Based Normalizing Flow For Speech Synthesis (2021)0.00
- Puffin: Pitch-synchronous Neural Waveform Generation For Fullband Speech On Modest Devices (2022)3.58
- Wasserstein GAN And Waveform Loss-based Acoustic Model Training For Multi-speaker Text-to-speech Synthesis Systems Using A Wavenet Vocoder (2018)12.61
- Empirical Evaluation Of Deep Learning Model Compression Techniques On The Wavenet Vocoder (2020)0.00
- FLY-TTS: Fast, Lightweight And High-quality End-to-end Text-to-speech Synthesis (2024)0.00
- Wavefit: An Iterative And Non-autoregressive Neural Vocoder Based On Fixed-point Iteration (2022)9.41