Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation
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_ | 1866929606197510144 |
|---|---|
| author | Wang, Pu Van hamme, Hugo |
| author_facet | Wang, Pu Van hamme, Hugo |
| contents | End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the explainable Disentangled-Transformer, which disentangles the internal representations into sub-embeddings with explicit content and speaker traits based on varying temporal resolutions. Experimental results show that the proposed Disentangled-Transformer produces a clear speaker identity, separated from the speech content, for speaker diarization while improving ASR performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17846 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation Wang, Pu Van hamme, Hugo Audio and Speech Processing End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the explainable Disentangled-Transformer, which disentangles the internal representations into sub-embeddings with explicit content and speaker traits based on varying temporal resolutions. Experimental results show that the proposed Disentangled-Transformer produces a clear speaker identity, separated from the speech content, for speaker diarization while improving ASR performance. |
| title | Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2411.17846 |