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

Recent speech technology research has seen a growing interest in usingWaveNets as statistical vocoders, i.e., generating speech waveforms fromacoustic features. These models have been shown to improve the generated speechquality over classical vocoders in many tasks, such as text-to-speech synthesisand voice conversion. Furthermore, conditioning WaveNets with acoustic featuresallows sharing the waveform generator model across multiple speakers withoutadditional speaker codes. However, multi-speaker WaveNet models require largeamounts of training data and computation to cover the entire acoustic space.This paper proposes leveraging the source-filter model of speech production tomore effectively train a speaker-independent waveform generator with limitedresources. We present a multi-speaker 'GlotNet' vocoder, which utilizes aWaveNet to generate glottal excitation waveforms, which are then used to excitethe corresponding vocal tract filter to produce speech. Listening tests showthat the proposed model performs favourably to a direct WaveNet vocoder trainedwith the same model architecture and data.

Speaker-independent raw waveform model for glottal excitation