Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech
In low-resource settings, deploying TTS typically requires choosing between a large voice-cloning model with costly inference or a compact fixed-voice system that requires a speaker-specific corpus. We study a third route: using a large voice-cloning model as a programmable data source to turn a short voice reference (e.g., 15 seconds) into a compact fixed-voice student trained entirely on synthetic speech. This setting makes pipeline design consequential: teacher errors become training targets, while filtering failed generations can reduce coverage of difficult texts. Thai further introduces challenges from ambiguous word boundaries, lexical tone, names and loanwords, numeric verbalizati...
| Authors | Kunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong et al. |
|---|---|
| Primary category | cs.CL |
| Published | 3 September 2026 |
| Last updated at source | 3 September 2026 |
Connected in the knowledge graph
- wayu-ai/wayu-paxa-tts-edgeModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.