تقرير
Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model
| العنوان: | Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model |
|---|---|
| المؤلفون: | Zezario, Ryandhimas E., Bai, Bo-Ren Brian, Fuh, Chiou-Shann, Wang, Hsin-Min, Tsao, Yu |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Sound |
| الوصف: | This study proposes a multi-task pseudo-label learning (MPL)-based non-intrusive speech quality assessment model called MTQ-Net. MPL consists of two stages: obtaining pseudo-label scores from a pretrained model and performing multi-task learning. The 3QUEST metrics, namely Speech-MOS (S-MOS), Noise-MOS (N-MOS), and General-MOS (G-MOS), are the assessment targets. The pretrained MOSA-Net model is utilized to estimate three pseudo labels: perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and speech distortion index (SDI). Multi-task learning is then employed to train MTQ-Net by combining a supervised loss (derived from the difference between the estimated score and the ground-truth label) and a semi-supervised loss (derived from the difference between the estimated score and the pseudo label), where the Huber loss is employed as the loss function. Experimental results first demonstrate the advantages of MPL compared to training a model from scratch and using a direct knowledge transfer mechanism. Second, the benefit of the Huber loss for improving the predictive ability of MTQ-Net is verified. Finally, the MTQ-Net with the MPL approach exhibits higher overall predictive power compared to other SSL-based speech assessment models. Comment: Accepted to IEEE ICASSP 2024 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2308.09262 |
| رقم الأكسشن: | edsarx.2308.09262 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |