English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Nowadays more and more applications can benefit from edge-basedtext-to-speech (TTS). However, most existing TTS models are too computationallyexpensive and are not flexible enough to be deployed on the diverse variety ofedge devices with their equally diverse computational capacities. To addressthis, we propose FBWave, a family of efficient and scalable neural vocodersthat can achieve optimal performance-efficiency trade-offs for different edgedevices. FBWave is a hybrid flow-based generative model that combines theadvantages of autoregressive and non-autoregressive models. It produces highquality audio and supports streaming during inference while remaining highlycomputationally efficient. Our experiments show that FBWave can achieve similaraudio quality to WaveRNN while reducing MACs by 40x. More efficient variants ofFBWave can achieve up to 109x fewer MACs while still delivering acceptableaudio quality. Audio demos are available athttps://bichenwu09.github.io/vocoder_demos.

FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge