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

In this paper, we propose a neural-based coding scheme in which an artificialneural network is exploited to automatically compress and decompress speechsignals by a trainable approach. Having a two-stage training phase, the systemcan be fully specified to each speech frame and have robust performance acrossdifferent speakers and wide range of spoken utterances. Indeed, Frame-basednonlinear predictive coding (FNPC) would code a frame in the procedure oftraining to predict the frame samples. The motivating objective is to analyzethe system behavior in regenerating not only the envelope of spectra, but alsothe spectra phase. This scheme has been evaluated in time and discrete cosinetransform (DCT) domains and the output of predicted phonemes show thepotentiality of the FNPC to reconstruct complicated signals. The experimentswere conducted on three voiced plosive phonemes, b/d/g/ in time and DCT domainsversus the number of neurons in the hidden layer. Experiments approve the FNPCcapability as an automatic coding system by which /b/d/g/ phonemes have beenreproduced with a good accuracy. Evaluations revealed that the performance ofFNPC system, trained to predict DCT coefficients is more desirable,particularly for frames with the wider distribution of energy, compared to timesamples.

A Robust Frame-based Nonlinear Prediction System for Automatic Speech Coding