Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.02073 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909981660413952 |
|---|---|
| author | Mohanta, Abhijit Remruatpuii Sarmah, Priyankoo Sinha, Rohit Lalhminghlui, Wendy |
| author_facet | Mohanta, Abhijit Remruatpuii Sarmah, Priyankoo Sinha, Rohit Lalhminghlui, Wendy |
| contents | This paper reports on the development of a text-to-speech (TTS) system for Mizo, a low-resource, tonal, and Tibeto-Burman language spoken primarily in the Indian state of Mizoram. The TTS was built with only 5.18 hours of data; however, in terms of subjective and objective evaluations, the outputs were considered perceptually acceptable and intelligible. A baseline model using Tacotron2 was built, and then, with the same data, another TTS model was built with VITS. In both subjective and objective evaluations, the VITS model outperformed the Tacotron2 model. In terms of tone synthesis, the VITS model showed significantly lower tone errors than the Tacotron2 model. The paper demonstrates that a non-autoregressive, end-to-end framework can achieve synthesis of acceptable perceptual quality and intelligibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02073 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Prosodically Informed Mizo TTS without Explicit Tone Markings Mohanta, Abhijit Remruatpuii Sarmah, Priyankoo Sinha, Rohit Lalhminghlui, Wendy Audio and Speech Processing This paper reports on the development of a text-to-speech (TTS) system for Mizo, a low-resource, tonal, and Tibeto-Burman language spoken primarily in the Indian state of Mizoram. The TTS was built with only 5.18 hours of data; however, in terms of subjective and objective evaluations, the outputs were considered perceptually acceptable and intelligible. A baseline model using Tacotron2 was built, and then, with the same data, another TTS model was built with VITS. In both subjective and objective evaluations, the VITS model outperformed the Tacotron2 model. In terms of tone synthesis, the VITS model showed significantly lower tone errors than the Tacotron2 model. The paper demonstrates that a non-autoregressive, end-to-end framework can achieve synthesis of acceptable perceptual quality and intelligibility. |
| title | Towards Prosodically Informed Mizo TTS without Explicit Tone Markings |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.02073 |