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

Neural network-based Text-to-Speech has significantly improved the quality ofsynthesized speech. Prominent methods (e.g., Tacotron2, FastSpeech, FastPitch)usually generate Mel-spectrogram from text and then synthesize speech usingvocoder (e.g., WaveNet, WaveGlow, HiFiGAN). Compared with traditionalparametric approaches (e.g., STRAIGHT and WORLD), neural vocoder basedend-to-end models suffer from slow inference speed, and the synthesized speechis usually not robust and lack of controllability. In this work, we propose anovel updated vocoder, which is a simple signal model to train and easy togenerate waveforms. We use the Gaussian-Markov model toward robust learning ofspectral envelope and wavelet-based statistical signal processing tocharacterize and decompose F0 features. It can retain the fine spectralenvelope and achieve high controllability of natural speech. The experimentalresults demonstrate that our proposed vocoder achieves better naturalness ofreconstructed speech than the conventional STRAIGHT vocoder, slightly betterthan WaveNet, and somewhat worse than the WaveRNN.

Towards Parametric Speech Synthesis Using Gaussian-Markov Model of Spectral Envelope and Wavelet-Based Decomposition of F0