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/

Zendy Plus

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

Zendy Tools

Zendy Open

In this paper, we propose a quasi-periodic neural network (QPNet) vocoderwith a novel network architecture named pitch-dependent dilated convolution(PDCNN) to improve the pitch controllability of WaveNet (WN) vocoder. Theeffectiveness of the WN vocoder to generate high-fidelity speech samples fromgiven acoustic features has been proved recently. However, because of the fixeddilated convolution and generic network architecture, the WN vocoder hardlygenerates speech with given F0 values which are outside the range observed intraining data. Consequently, the WN vocoder lacks the pitch controllabilitywhich is one of the essential capabilities of conventional vocoders. To addressthis limitation, we propose the PDCNN component which has the time-variantadaptive dilation size related to the given F0 values and a cascade networkstructure of the QPNet vocoder to generate quasi-periodic signals such asspeech. Both objective and subjective tests are conducted, and the experimentalresults demonstrate the better pitch controllability of the QPNet vocodercompared to the same and double sized WN vocoders while attaining comparablespeech qualities. Index Terms: WaveNet, vocoder, quasi-periodic signal,pitch-dependent dilated convolution, pitch controllability

Quasi-Periodic WaveNet Vocoder: A Pitch Dependent Dilated Convolution Model for Parametric Speech Generation