Continual Learning in Machine Speech Chain Using Gradient Episodic Memory
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910718722310144 |
|---|---|
| author | Tyndall, Geoffrey Azizah, Kurniawati Tanaya, Dipta Purwarianti, Ayu Lestari, Dessi Puji Sakti, Sakriani |
| author_facet | Tyndall, Geoffrey Azizah, Kurniawati Tanaya, Dipta Purwarianti, Ayu Lestari, Dessi Puji Sakti, Sakriani |
| contents | Continual learning for automatic speech recognition (ASR) systems poses a challenge, especially with the need to avoid catastrophic forgetting while maintaining performance on previously learned tasks. This paper introduces a novel approach leveraging the machine speech chain framework to enable continual learning in ASR using gradient episodic memory (GEM). By incorporating a text-to-speech (TTS) component within the machine speech chain, we support the replay mechanism essential for GEM, allowing the ASR model to learn new tasks sequentially without significant performance degradation on earlier tasks. Our experiments, conducted on the LJ Speech dataset, demonstrate that our method outperforms traditional fine-tuning and multitask learning approaches, achieving a substantial error rate reduction while maintaining high performance across varying noise conditions. We showed the potential of our semi-supervised machine speech chain approach for effective and efficient continual learning in speech recognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_18320 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Continual Learning in Machine Speech Chain Using Gradient Episodic Memory Tyndall, Geoffrey Azizah, Kurniawati Tanaya, Dipta Purwarianti, Ayu Lestari, Dessi Puji Sakti, Sakriani Computation and Language Artificial Intelligence Audio and Speech Processing Continual learning for automatic speech recognition (ASR) systems poses a challenge, especially with the need to avoid catastrophic forgetting while maintaining performance on previously learned tasks. This paper introduces a novel approach leveraging the machine speech chain framework to enable continual learning in ASR using gradient episodic memory (GEM). By incorporating a text-to-speech (TTS) component within the machine speech chain, we support the replay mechanism essential for GEM, allowing the ASR model to learn new tasks sequentially without significant performance degradation on earlier tasks. Our experiments, conducted on the LJ Speech dataset, demonstrate that our method outperforms traditional fine-tuning and multitask learning approaches, achieving a substantial error rate reduction while maintaining high performance across varying noise conditions. We showed the potential of our semi-supervised machine speech chain approach for effective and efficient continual learning in speech recognition. |
| title | Continual Learning in Machine Speech Chain Using Gradient Episodic Memory |
| topic | Computation and Language Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2411.18320 |