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

WaveCycleGAN has recently been proposed to bridge the gap between natural andsynthesized speech waveforms in statistical parametric speech synthesis andprovides fast inference with a moving average model rather than anautoregressive model and high-quality speech synthesis with the adversarialtraining. However, the human ear can still distinguish the processed speechwaveforms from natural ones. One possible cause of this distinguishability isthe aliasing observed in the processed speech waveform via down/up-samplingmodules. To solve the aliasing and provide higher quality speech synthesis, wepropose WaveCycleGAN2, which 1) uses generators without down/up-samplingmodules and 2) combines discriminators of the waveform domain and acousticparameter domain. The results show that the proposed method 1) alleviates thealiasing well, 2) is useful for both speech waveforms generated byanalysis-and-synthesis and statistical parametric speech synthesis, and 3)achieves a mean opinion score comparable to those of natural speech and speechsynthesized by WaveNet (open WaveNet) and WaveGlow while processing speechsamples at a rate of more than 150 kHz on an NVIDIA Tesla P100.

WaveCycleGAN2: Time-domain Neural Post-filter for Speech Waveform Generation