MiLex performs unsupervised learning and prediction of primary lexical stress starting from continuous speech data and its orthographic transcript. It uses a method  based on syllable nuclei approximation and stress detection using simple acoustic features.

The toolkit is intended to be used in the development of text-to-speech (TTS) synthesis systems for under-resourced languages with the scope to improve the naturalness and intelligibility in TTS synthesis systems.

[Download]