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 study proposes a multi-task pseudo-label learning (MPL)-basednon-intrusive speech quality assessment model called MTQ-Net. MPL consists oftwo stages: obtaining pseudo-label scores from a pretrained model andperforming multi-task learning. The 3QUEST metrics, namely Speech-MOS (S-MOS),Noise-MOS (N-MOS), and General-MOS (G-MOS), are the assessment targets. Thepretrained MOSA-Net model is utilized to estimate three pseudo labels:perceptual evaluation of speech quality (PESQ), short-time objectiveintelligibility (STOI), and speech distortion index (SDI). Multi-task learningis then employed to train MTQ-Net by combining a supervised loss (derived fromthe difference between the estimated score and the ground-truth label) and asemi-supervised loss (derived from the difference between the estimated scoreand the pseudo label), where the Huber loss is employed as the loss function.Experimental results first demonstrate the advantages of MPL compared totraining a model from scratch and using a direct knowledge transfer mechanism.Second, the benefit of the Huber loss for improving the predictive ability ofMTQ-Net is verified. Finally, the MTQ-Net with the MPL approach exhibits higheroverall predictive power compared to other SSL-based speech assessment models.

Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model