Adaptive Duration Model for Text Speech Alignment
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915469841137664 |
|---|---|
| author | Cao, Junjie |
| author_facet | Cao, Junjie |
| contents | Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line, while non-autoregressive end to end TTS models rely on durations extracted from external sources. In this paper, we propose a novel duration prediction framework that can give promising phoneme-level duration distribution with given text. In our experiments, the proposed duration model has more precise prediction and adaptation ability to conditions, compared to previous baseline models. Specifically, it makes a considerable improvement on phoneme-level alignment accuracy and makes the performance of zero-shot TTS models more robust to the mismatch between prompt audio and input audio. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22612 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive Duration Model for Text Speech Alignment Cao, Junjie Sound Artificial Intelligence Audio and Speech Processing Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line, while non-autoregressive end to end TTS models rely on durations extracted from external sources. In this paper, we propose a novel duration prediction framework that can give promising phoneme-level duration distribution with given text. In our experiments, the proposed duration model has more precise prediction and adaptation ability to conditions, compared to previous baseline models. Specifically, it makes a considerable improvement on phoneme-level alignment accuracy and makes the performance of zero-shot TTS models more robust to the mismatch between prompt audio and input audio. |
| title | Adaptive Duration Model for Text Speech Alignment |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.22612 |