Updating only encoders prevents catastrophic forgetting of end-to-end ASR models

Y Takashima, S Horiguchi, S Watanabe… - arXiv preprint arXiv …, 2022 - arxiv.org
In this paper, we present an incremental domain adaptation technique to prevent
catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model …
被引用次数：5 相关文章
[PDF] isca-archive.org

[PDF][PDF] Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models

Y Takashima, S Horiguchi, S Watanabe, P Garcıa… - 2022 - isca-archive.org
In this paper, we present an incremental domain adaptation technique to prevent
catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model …

Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models

Y Takashima, S Horiguchi… - Proceedings of the …, 2022 - waseda.elsevierpure.com
抄録 In this paper, we present an incremental domain adaptation technique to prevent
catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model …

Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models

Y Takashima, S Horiguchi, S Watanabe… - arXiv e …, 2022 - ui.adsabs.harvard.edu
In this paper, we present an incremental domain adaptation technique to prevent
catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model …

Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models

Y Takashima, S Horiguchi… - Proceedings of the …, 2022 - waseda.elsevierpure.com
In this paper, we present an incremental domain adaptation technique to prevent
catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model …