Continual Learning for Monolingual End-to-End Automatic Speech Recognition

2021-12-17 · Steven Vander Eeckt, Hugo Van hamme

Adapting Automatic Speech Recognition (ASR) models to new domains results in a deterioration of performance on the original domain(s), a phenomenon called Catastrophic Forgetting (CF). Even monolingual ASR models cannot be extended to new accents, dialects, topics, etc. without suffering from CF, making them unable to be continually enhanced without storing all past data. Fortunately, Continual Learning (CL) methods, which aim to enable continual adaptation while overcoming CF, can be used. In this paper, we implement an extensive number of CL methods for End-to-End ASR and test and compare their ability to extend a monolingual Hybrid CTC-Transformer model across four new tasks. We find that the best performing CL method closes the gap between the fine-tuned model (lower bound) and the model trained jointly on all tasks (upper bound) by more than 40%, while requiring access to only 0.6% of the original data.

📄 PDF Abstract BibTeX arXiv:2112.09427

Code (1)

stevenvdeeckt/cgn_cl_dialect 공식 구현

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Continual Learning speech-recognition Speech Recognition

Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition

2022-10-27 · Steven Vander Eeckt, Hugo Van hamme

Adapting a trained Automatic Speech Recognition (ASR) model to new tasks results in catastrophic forgetting of old tasks, limiting the model's ability to learn continually and to be extended to new speakers, dialects, la…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Knowledge Distillation speech-recognition+1

Online Continual Learning of End-to-End Speech Recognition Models

2022-07-11 · Muqiao Yang, Ian Lane, Shinji Watanabe

Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptati…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Continual Learning Lifelong learning+3

Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition

2020-06-01 · Sanket Shah, Basil Abraham, Gurunath Reddy M, Sunayana Sitaram 외

Recently, there has been significant progress made in Automatic Speech Recognition (ASR) of code-switched speech, leading to gains in accuracy on code-switched datasets in many language pairs. Code-switched speech co-occ…

Automatic Speech Recognition Automatic Speech Recognition (ASR)speech-recognition Speech Recognition

Towards End-to-end Automatic Code-Switching Speech Recognition

2018-10-30 · Genta Indra Winata, Andrea Madotto, Chien-Sheng Wu, Pascale Fung

Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as "one" in English and "w\`an" in Chinese. We propose a C…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Language Modeling Language Modelling+2

Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition

2020-06-09 · Gurunath Reddy Madhumani, Sanket Shah, Basil Abraham, Vikas Joshi 외

Recognizing code-switched speech is challenging for Automatic Speech Recognition (ASR) for a variety of reasons, including the lack of code-switched training data. Recently, we showed that monolingual ASR systems fine-tu…