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

Automatic speech recognition systems usually rely on spectral-based features,such as MFCC of PLP. These features are extracted based on prior knowledge suchas, speech perception or/and speech production. Recently, convolutional neuralnetworks have been shown to be able to estimate phoneme conditionalprobabilities in a completely data-driven manner, i.e. using directly temporalraw speech signal as input. This system was shown to yield similar or betterperformance than HMM/ANN based system on phoneme recognition task and on largescale continuous speech recognition task, using less parameters. Motivated bythese studies, we investigate the use of simple linear classifier in theCNN-based framework. Thus, the network learns linearly separable features fromraw speech. We show that such system yields similar or better performance thanMLP based system using cepstral-based features as input.

Learning linearly separable features for speech recognition using convolutional neural networks