| 講演抄録/キーワード |
| 講演名 |
2023-12-03 11:05
[ポスター講演]Enhancing Multi-Accent Automated Speech Recognition with Accent-Activated Adapters ○Yuqin Lin・Longbiao Wang・Jianwu Dang(Tianjin Univ. & Univ. of Tokyo)・Nobuaki Minematsu(Univ. of Tokyo) NLC2023-18 SP2023-38 |
| 抄録 |
(和) |
This paper proposes the Accent-Activated adapter (AccentAct) approach to address the challenge of speech variations in multi-accent scenarios. By incorporating parallel accent and contextual extractors within a pre-trained model, AccentAct improves ASR performance while reducing computational resources. Experimental results show that AccentAct outperforms traditional methods with a significant reduction in computational requirements, promoting inclusivity for individuals with diverse accents or dialects. |
| (英) |
This paper proposes the Accent-Activated adapter (AccentAct) approach to address the challenge of speech variations in multi-accent scenarios. By incorporating parallel accent and contextual extractors within a pre-trained model, AccentAct improves ASR performance while reducing computational resources. Experimental results show that AccentAct outperforms traditional methods with a significant reduction in computational requirements, promoting inclusivity for individuals with diverse accents or dialects. |
| キーワード |
(和) |
Automatic speech recognition / accented speech / adaptation / / / / / |
| (英) |
Automatic speech recognition / accented speech / adaptation / / / / / |
| 文献情報 |
信学技報, vol. 123, no. 292, SP2023-38, pp. 25-30, 2023年12月. |
| 資料番号 |
SP2023-38 |
| 発行日 |
2023-11-25 (NLC, SP) |
| ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
| PDFダウンロード |
NLC2023-18 SP2023-38 |