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

The perceptual task of speech quality assessment (SQA) is a challenging taskfor machines to do. Objective SQA methods that rely on the availability of thecorresponding clean reference have been the primary go-to approaches for SQA.Clearly, these methods fail in real-world scenarios where the ground truthclean references are not available. In recent years, non-intrusive methods thattrain neural networks to predict ratings or scores have attracted muchattention, but they suffer from several shortcomings such as lack ofrobustness, reliance on labeled data for training and so on. In this work, wepropose a new direction for speech quality assessment. Inspired by human'sinnate ability to compare and assess the quality of speech signals even whenthey have non-matching contents, we propose a novel framework that predicts asubjective relative quality score for the given speech signal with respect toany provided reference without using any subjective data. We show that neuralnetworks trained using our framework produce scores that correlate well withsubjective mean opinion scores (MOS) and are also competitive to methods suchas DNSMOS, which explicitly relies on MOS from humans for training networks.Moreover, our method also provides a natural way to embed quality-relatedinformation in neural networks, which we show is helpful for downstream taskssuch as speech enhancement.

NORESQA: A Framework for Speech Quality Assessment using Non-Matching References