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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Speech recognition systems have achieved high recognition performance forseveral tasks. However, the performance of such systems is dependent on thetremendously costly development work of preparing vast amounts of task-matchedtranscribed speech data for supervised training. The key problem here is thecost of transcribing speech data. The cost is repeatedly required to supportnew languages and new tasks. Assuming broad network services for transcribingspeech data for many users, a system would become more self-sufficient and moreuseful if it possessed the ability to learn from very light feedback from theusers without annoying them. In this paper, we propose a general reinforcementlearning framework for speech recognition systems based on the policy gradientmethod. As a particular instance of the framework, we also propose a hypothesisselection-based reinforcement learning method. The proposed framework providesa new view for several existing training and adaptation methods. Theexperimental results show that the proposed method improves the recognitionperformance compared to unsupervised adaptation.

Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection