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

We study large-scale kernel methods for acoustic modeling and compare to DNNson performance metrics related to both acoustic modeling and recognition.Measuring perplexity and frame-level classification accuracy, kernel-basedacoustic models are as effective as their DNN counterparts. However, ontoken-error-rates DNN models can be significantly better. We have discoveredthat this might be attributed to DNN's unique strength in reducing both theperplexity and the entropy of the predicted posterior probabilities. Motivatedby our findings, we propose a new technique, entropy regularized perplexity,for model selection. This technique can noticeably improve the recognitionperformance of both types of models, and reduces the gap between them. Whileeffective on Broadcast News, this technique could be also applicable to othertasks.

A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition