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

This paper explores the use of multi-view features and their discriminativetransforms in a convolutional deep neural network (CNN) architecture for acontinuous large vocabulary speech recognition task. Mel-filterbank energiesand perceptually motivated forced damped oscillator coefficient (DOC) featuresare used after feature-space maximum-likelihood linear regression (fMLLR)transforms, which are combined and fed as a multi-view feature to a single CNNacoustic model. Use of multi-view feature representation demonstratedsignificant reduction in word error rates (WERs) compared to the use ofindividual features by themselves. In addition, when articulatory informationwas used as an additional input to a fused deep neural network (DNN) and CNNacoustic model, it was found to demonstrate further reduction in WER for theSwitchboard subset and the CallHome subset (containing partly non-nativeaccented speech) of the NIST 2000 conversational telephone speech test set,reducing the error rate by 12% relative to the baseline in both cases. Thiswork shows that multi-view features in association with articulatoryinformation can improve speech recognition robustness to spontaneous andnon-native speech.

Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition