One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech
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_ | 1866908999682621440 |
|---|---|
| author | Abebe, Amanuel Gizachew Moslem, Yasmin |
| author_facet | Abebe, Amanuel Gizachew Moslem, Yasmin |
| contents | Preserving a speaker's voice identity while generating speech in a different language remains a fundamental challenge in spoken language technology, particularly in specialized domains such as scientific communication. In this paper, we address this challenge through our system submission to the International Conference on Spoken Language Translation (IWSLT 2026), the Cross-Lingual Voice Cloning shared task. First, we evaluate several state-of-the-art voice cloning models for cross-lingual speech generation of scientific texts in Arabic, Chinese, and French. Then, we build voice cloning systems based on the OmniVoice foundation model. We employ data augmentation via multi-model ensemble distillation from the ACL 60/60 corpus. We investigate the effect of using this synthetic data for fine-tuning, demonstrating consistent improvements in intelligibility (WER and CER) across languages while preserving speaker similarity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26136 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech Abebe, Amanuel Gizachew Moslem, Yasmin Audio and Speech Processing Computation and Language Preserving a speaker's voice identity while generating speech in a different language remains a fundamental challenge in spoken language technology, particularly in specialized domains such as scientific communication. In this paper, we address this challenge through our system submission to the International Conference on Spoken Language Translation (IWSLT 2026), the Cross-Lingual Voice Cloning shared task. First, we evaluate several state-of-the-art voice cloning models for cross-lingual speech generation of scientific texts in Arabic, Chinese, and French. Then, we build voice cloning systems based on the OmniVoice foundation model. We employ data augmentation via multi-model ensemble distillation from the ACL 60/60 corpus. We investigate the effect of using this synthetic data for fine-tuning, demonstrating consistent improvements in intelligibility (WER and CER) across languages while preserving speaker similarity. |
| title | One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech |
| topic | Audio and Speech Processing Computation and Language |
| url | https://arxiv.org/abs/2604.26136 |