Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914857515745280 |
|---|---|
| author | Chen, Jinming Fang, Jingyi Zheng, Yuanzhong Wang, Yaoxuan Fei, Haojun |
| author_facet | Chen, Jinming Fang, Jingyi Zheng, Yuanzhong Wang, Yaoxuan Fei, Haojun |
| contents | Currently, end-to-end (E2E) speech recognition methods have achieved promising performance. However, auto speech recognition (ASR) models still face challenges in recognizing multi-accent speech accurately. We propose a layer-adapted fusion (LAF) model, called Qifusion-Net, which does not require any prior knowledge about the target accent. Based on dynamic chunk strategy, our approach enables streaming decoding and can extract frame-level acoustic feature, facilitating fine-grained information fusion. Experiment results demonstrate that our proposed methods outperform the baseline with relative reductions of 22.1$\%$ and 17.2$\%$ in character error rate (CER) across multi accent test datasets on KeSpeech and MagicData-RMAC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03026 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition Chen, Jinming Fang, Jingyi Zheng, Yuanzhong Wang, Yaoxuan Fei, Haojun Sound Artificial Intelligence Audio and Speech Processing Currently, end-to-end (E2E) speech recognition methods have achieved promising performance. However, auto speech recognition (ASR) models still face challenges in recognizing multi-accent speech accurately. We propose a layer-adapted fusion (LAF) model, called Qifusion-Net, which does not require any prior knowledge about the target accent. Based on dynamic chunk strategy, our approach enables streaming decoding and can extract frame-level acoustic feature, facilitating fine-grained information fusion. Experiment results demonstrate that our proposed methods outperform the baseline with relative reductions of 22.1$\%$ and 17.2$\%$ in character error rate (CER) across multi accent test datasets on KeSpeech and MagicData-RMAC. |
| title | Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.03026 |