In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving …
Although large foundation models pre-trained by self-supervised learning have achieved state-of-the-art performance in many tasks including automatic speech recognition (ASR) …
R Masumura, M Ihori, A Takashima… - 2020 Asia-Pacific …, 2020 - ieeexplore.ieee.org
This paper is the first study to apply deep mutual learning (DML) to end-to-end ASR models. In DML, multiple models are trained simultaneously and collaboratively by mimicking each …
Most automatic speech recognition (ASR) neural network models are not suitable for mobile devices due to their large model sizes. Therefore, it is required to reduce the model size to …
M Han, F Chen, J Shi, S Xu, B Xu - arXiv preprint arXiv:2301.13003, 2023 - arxiv.org
Large-scale pre-trained language models (PLMs) have shown great potential in natural language processing tasks. Leveraging the capabilities of PLMs to enhance automatic …
Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of …
JW Yoon, BJ Woo, S Ahn, H Lee… - 2022 IEEE Spoken …, 2023 - ieeexplore.ieee.org
Recently, the advance in deep learning has brought a considerable improvement in the end- to-end speech recognition field, simplifying the traditional pipeline while producing …
Knowledge distillation is an effective machine learning technique to transfer knowledge from a teacher model to a smaller student model, especially with unlabeled data. In this paper, we …
L Fu, X Li, L Zi, Z Zhang, Y Wu, X He… - 2021 IEEE Automatic …, 2021 - ieeexplore.ieee.org
In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while …