Developing TTS
This pages gives an overview of production of text-to-speech (TTS) programs for minority languages. Programs built so far can be found at the Borealium resource page.
Phases in the production process
- Collecting and preparing text to be used (several months)
- Recording tehe texts (one week of studio time)
- Text postprocessing (months)
- Splitting the recordings and text transcripts to approx. sentence-long individual files
- Procedures for normalisation of input text
- Building a voice
- Combining parts and distribution
Resources
- overview of existing resources
- ESpeakNG