Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909135294955520 |
|---|---|
| author | Zezario, Ryandhimas E. Bai, Bo-Ren Brian Fuh, Chiou-Shann Wang, Hsin-Min Tsao, Yu |
| author_facet | Zezario, Ryandhimas E. Bai, Bo-Ren Brian Fuh, Chiou-Shann Wang, Hsin-Min Tsao, Yu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_09262 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model Zezario, Ryandhimas E. Bai, Bo-Ren Brian Fuh, Chiou-Shann Wang, Hsin-Min Tsao, Yu Audio and Speech Processing Machine Learning Sound 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. |
| title | Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2308.09262 |