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

With the evolution of neural network based methods, automatic speechrecognition (ASR) field has been advanced to a level where building anapplication with speech interface is a reality. In spite of these advances,building a real-time speech recogniser faces several problems such as lowrecognition accuracy, domain constraint, and out-of-vocabulary words. The lowrecognition accuracy problem is addressed by improving the acoustic model,language model, decoder and by rescoring the N-best list at the output of thedecoder. We are considering the N-best list rescoring approach to improve therecognition accuracy. Most of the methods in the literature use thegrammatical, lexical, syntactic and semantic connection between the words in arecognised sentence as a feature to rescore. In this paper, we have tried tosee the semantic relatedness between the words in a sentence to rescore theN-best list. Semantic relatedness is computed usingTransE~\cite{bordes2013translating}, a method for low dimensional embedding ofa triple in a knowledge graph. The novelty of the paper is the application ofsemantic web to automatic speech recognition.

Use of Knowledge Graph in Rescoring the N-Best List in Automatic Speech Recognition