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 (ASR) systems are evaluated using Word ErrorRate (WER), which is calculated by comparing the number of errors between theground truth and the transcription of the ASR system. This calculation,however, requires manual transcription of the speech signal to obtain theground truth. Since transcribing audio signals is a costly process, AutomaticWER Evaluation (e-WER) methods have been developed to automatically predict theWER of a speech system by only relying on the transcription and the speechsignal features. While WER is a continuous variable, previous works have shownthat positing e-WER as a classification problem is more effective thanregression. However, while converting to a classification setting, theseapproaches suffer from heavy class imbalance. In this paper, we propose a newbalanced paradigm for e-WER in a classification setting. Within this paradigm,we also propose WER-BERT, a BERT based architecture with speech features fore-WER. Furthermore, we introduce a distance loss function to tackle the ordinalnature of e-WER classification. The proposed approach and paradigm areevaluated on the Librispeech dataset and a commercial (black box) ASR system,Google Cloud's Speech-to-Text API. The results and experiments demonstrate thatWER-BERT establishes a new state-of-the-art in automatic WER estimation.

WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm