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

With the number of smart devices increasing, the demand for on-devicetext-to-speech (TTS) increases rapidly. In recent years, many prominentEnd-to-End TTS methods have been proposed, and have greatly improved thequality of synthesized speech. However, to ensure the qualified speech, mostTTS systems depend on large and complex neural network models, and it's hard todeploy these TTS systems on-device. In this paper, a small-footprint, fast,stable network for on-device TTS is proposed, named as DeviceTTS. DeviceTTSmakes use of a duration predictor as a bridge between encoder and decoder so asto avoid the problem of words skipping and repeating in Tacotron. As we allknow, model size is a key factor for on-device TTS. For DeviceTTS, DeepFeedforward Sequential Memory Network (DFSMN) is used as the basic component.Moreover, to speed up inference, mix-resolution decoder is proposed for balancethe inference speed and speech quality. Experiences are done with WORLD andLPCNet vocoder. Finally, with only 1.4 million model parameters and 0.099GFLOPS, DeviceTTS achieves comparable performance with Tacotron and FastSpeech.As far as we know, the DeviceTTS can meet the needs of most of the devices inpractical application.

DeviceTTS: A Small-Footprint, Fast, Stable Network for On-Device Text-to-Speech