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 research introduces an enhanced version of the multi-objective speechassessment model, called MOSA-Net+, by leveraging the acoustic features fromlarge pre-trained weakly supervised models, namely Whisper, to create embeddingfeatures. The first part of this study investigates the correlation between theembedding features of Whisper and two self-supervised learning (SSL) modelswith subjective quality and intelligibility scores. The second part evaluatesthe effectiveness of Whisper in deploying a more robust speech assessmentmodel. Third, the possibility of combining representations from Whisper and SSLmodels while deploying MOSA-Net+ is analyzed. The experimental results revealthat Whisper's embedding features correlate more strongly with subjectivequality and intelligibility than other SSL's embedding features, contributingto more accurate prediction performance achieved by MOSA-Net+. Moreover,combining the embedding features from Whisper and SSL models only leads tomarginal improvement. As compared to MOSA-Net and other SSL-based speechassessment models, MOSA-Net+ yields notable improvements in estimatingsubjective quality and intelligibility scores across all evaluation metrics. Wefurther tested MOSA-Net+ on Track 3 of the VoiceMOS Challenge 2023 and obtainedthe top-ranked performance.

A Study on Incorporating Whisper for Robust Speech Assessment