paper-with-me

홈 › Papers

Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition

2023-12-20 · Ashish Seth, Sreyan Ghosh, S. Umesh, Dinesh Manocha

Continued self-supervised (SSL) pre-training for adapting existing SSL models to the target domain has shown to be extremely effective for low-resource Automatic Speech Recognition (ASR). This paper proposes Stable Distillation, a simple and novel approach for SSL-based continued pre-training that boosts ASR performance in the target domain where both labeled and unlabeled data are limited. Stable Distillation employs self-distillation as regularization for continued pre-training, alleviating the over-fitting issue, a common problem continued pre-training faces when the source and target domains differ. Specifically, first, we perform vanilla continued pre-training on an initial SSL pre-trained model on the target domain ASR dataset and call it the teacher. Next, we take the same initial pre-trained model as a student to perform continued pre-training while enforcing its hidden representations to be close to that of the teacher (via MSE loss). This student is then used for downstream ASR fine-tuning on the target dataset. In practice, Stable Distillation outperforms all our baselines by 0.8 - 7 WER when evaluated in various experimental settings.

📄 PDF Abstract BibTeX arXiv:2312.12783

Code (1)

cs20s030/stable_distillation 공식 구현 pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Regularizing Class-wise Predictions via Self-knowledge Distillation

2020-03-31 · CVPR 2020 6 · Sukmin Yun, Jongjin Park, Kimin Lee, Jinwoo Shin

Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between si…

image-classificationImage ClassificationKnowledge DistillationSelf-Knowledge Distillation

Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpus

2024-10-18 · Raviraj Joshi, Kanishk Singla, Anusha Kamath, Raunak Kalani 외

Multilingual LLMs support a variety of languages; however, their performance is suboptimal for low-resource languages. In this work, we emphasize the importance of continued pre-training of multilingual LLMs and the use …

Efficient training for compact compression models via sequential distillation

2026-01-09 · Caroline Mazini Rodrigues, Nicolas Keriven, Thomas Maugey arxiv

Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and r…

Knowledge DistillationImage Compression

DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining

2025-09-02 · Bryan Rodas, Natalie Montesino, Jakob Ambsdorf, David Klindt 외 arxiv

Continued pretraining offers a promising solution for adapting foundation models to a new target domain. However, in specialized domains, available datasets are often very small, limiting the applicability of SSL methods…

Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models

2024-07-09 · Jupinder Parmar, Sanjev Satheesh, Mostofa Patwary, Mohammad Shoeybi 외

As language models have scaled both their number of parameters and pretraining dataset sizes, the computational cost for pretraining has become intractable except for the most well-resourced teams. This increasing cost m…