Aligner-Guided Training Paradigm: Advancing Text-to-Speech Models with Aligner Guided Duration
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_ | 1866916518150799360 |
|---|---|
| author | Lou, Haowei Paik, Helen Hu, Wen Yao, Lina |
| author_facet | Lou, Haowei Paik, Helen Hu, Wen Yao, Lina |
| contents | Recent advancements in text-to-speech (TTS) systems, such as FastSpeech and StyleSpeech, have significantly improved speech generation quality. However, these models often rely on duration generated by external tools like the Montreal Forced Aligner, which can be time-consuming and lack flexibility. The importance of accurate duration is often underestimated, despite their crucial role in achieving natural prosody and intelligibility. To address these limitations, we propose a novel Aligner-Guided Training Paradigm that prioritizes accurate duration labelling by training an aligner before the TTS model. This approach reduces dependence on external tools and enhances alignment accuracy. We further explore the impact of different acoustic features, including Mel-Spectrograms, MFCCs, and latent features, on TTS model performance. Our experimental results show that aligner-guided duration labelling can achieve up to a 16\% improvement in word error rate and significantly enhance phoneme and tone alignment. These findings highlight the effectiveness of our approach in optimizing TTS systems for more natural and intelligible speech generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08112 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Aligner-Guided Training Paradigm: Advancing Text-to-Speech Models with Aligner Guided Duration Lou, Haowei Paik, Helen Hu, Wen Yao, Lina Sound Artificial Intelligence Computation and Language Machine Learning Audio and Speech Processing Recent advancements in text-to-speech (TTS) systems, such as FastSpeech and StyleSpeech, have significantly improved speech generation quality. However, these models often rely on duration generated by external tools like the Montreal Forced Aligner, which can be time-consuming and lack flexibility. The importance of accurate duration is often underestimated, despite their crucial role in achieving natural prosody and intelligibility. To address these limitations, we propose a novel Aligner-Guided Training Paradigm that prioritizes accurate duration labelling by training an aligner before the TTS model. This approach reduces dependence on external tools and enhances alignment accuracy. We further explore the impact of different acoustic features, including Mel-Spectrograms, MFCCs, and latent features, on TTS model performance. Our experimental results show that aligner-guided duration labelling can achieve up to a 16\% improvement in word error rate and significantly enhance phoneme and tone alignment. These findings highlight the effectiveness of our approach in optimizing TTS systems for more natural and intelligible speech generation. |
| title | Aligner-Guided Training Paradigm: Advancing Text-to-Speech Models with Aligner Guided Duration |
| topic | Sound Artificial Intelligence Computation and Language Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2412.08112 |