Lombard Speech Synthesis for Any Voice with Controllable Style Embeddings
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912832137723904 |
|---|---|
| author | Akti, Seymanur Waibel, Alexander |
| author_facet | Akti, Seymanur Waibel, Alexander |
| contents | The Lombard effect plays a key role in natural communication, particularly in noisy environments or when addressing hearing-impaired listeners. We present a controllable text-to-speech (TTS) system capable of synthesizing Lombard speech for any speaker without requiring explicit Lombard data during training. Our approach leverages style embeddings learned from a large, prosodically diverse dataset and analyzes their correlation with Lombard attributes using principal component analysis (PCA). By shifting the relevant PCA components, we manipulate the style embeddings and incorporate them into our TTS model to generate speech at desired Lombard levels. Evaluations demonstrate that our method preserves naturalness and speaker identity, enhances intelligibility under noise, and provides fine-grained control over prosody, offering a robust solution for controllable Lombard TTS for any speaker. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12966 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Lombard Speech Synthesis for Any Voice with Controllable Style Embeddings Akti, Seymanur Waibel, Alexander Sound Computation and Language The Lombard effect plays a key role in natural communication, particularly in noisy environments or when addressing hearing-impaired listeners. We present a controllable text-to-speech (TTS) system capable of synthesizing Lombard speech for any speaker without requiring explicit Lombard data during training. Our approach leverages style embeddings learned from a large, prosodically diverse dataset and analyzes their correlation with Lombard attributes using principal component analysis (PCA). By shifting the relevant PCA components, we manipulate the style embeddings and incorporate them into our TTS model to generate speech at desired Lombard levels. Evaluations demonstrate that our method preserves naturalness and speaker identity, enhances intelligibility under noise, and provides fine-grained control over prosody, offering a robust solution for controllable Lombard TTS for any speaker. |
| title | Lombard Speech Synthesis for Any Voice with Controllable Style Embeddings |
| topic | Sound Computation and Language |
| url | https://arxiv.org/abs/2601.12966 |