paper-with-me

홈 › Papers

Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality Assessment

2025-02-07 · Benjamin Stahl, Hannes Gamper

In this paper, we investigate distillation and pruning methods to reduce model size for non-intrusive speech quality assessment based on self-supervised representations. Our experiments build on XLS-R-SQA, a speech quality assessment model using wav2vec 2.0 XLS-R embeddings. We retrain this model on a large compilation of mean opinion score datasets, encompassing over 100,000 labeled clips. For distillation, using this model as a teacher, we generate pseudo-labels on unlabeled degraded speech signals and train student models of varying sizes. For pruning, we use a data-driven strategy. While data-driven pruning performs better at larger model sizes, distillation on unlabeled data is more effective for smaller model sizes. Distillation can halve the gap between the baseline's correlation with ground-truth MOS labels and that of the XLS-R-based teacher model, while reducing model size by two orders of magnitude compared to the teacher model.

📄 PDF Abstract BibTeX arXiv:2502.05356

Code (1)

microsoft/Distill-MOS 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Deep Neural Compression Via Concurrent Pruning and Self-Distillation

2021-09-30 · James O' Neill, Sourav Dutta, Haytham Assem

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational simila…

Knowledge DistillationLanguage ModelingLanguage Modelling

Self-Distilled Pruning Of Neural Networks

2021-09-29 · James O' Neill, Sourav Dutta, Haytham Assem

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational simila…

Knowledge DistillationLanguage ModelingLanguage Modelling

Self-Distilled Pruning of Neural Networks

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational simila…

Knowledge DistillationLanguage ModelingLanguage Modelling

Aligned Weight Regularizers for Pruning Pretrained Neural Networks

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational simila…

Knowledge DistillationLanguage ModelingLanguage Modelling

DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models

2023-05-28 · Yifan Peng, Yui Sudo, Shakeel Muhammad, Shinji Watanabe

Self-supervised learning (SSL) has achieved notable success in many speech processing tasks, but the large model size and heavy computational cost hinder the deployment. Knowledge distillation trains a small student mode…

Knowledge DistillationSelf-Supervised Learning