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 source-filter (NSF) models are deep neural networks that producewaveforms given input acoustic features. They use dilated-convolution-basedneural filter modules to filter sine-based excitation for waveform generation,which is different from WaveNet and flow-based models. One of the NSF models,called harmonic-plus-noise NSF (h-NSF) model, uses separate pairs of source andneural filters to generate harmonic and noise waveform components. It is closeto WaveNet in terms of speech quality while being superior in generation speed.  The h-NSF model can be improved even further. While h-NSF merges the harmonicand noise components using pre-defined digital low- and high-pass filters, itis well known that the maximum voice frequency (MVF) that separates theperiodic and aperiodic spectral bands are time-variant. Therefore, we propose anew h-NSF model with time-variant and trainable MVF. We parameterize thedigital low- and high-pass filters as windowed-sinc filters and predict theircut-off frequency (i.e., MVF) from the input acoustic features. Our experimentsdemonstrated that the new model can predict a good trajectory of the MVF andproduce high-quality speech for a text-to-speech synthesis system.

Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis