Gnuspeech is an extensible, text-to-speech package, based on real-time, articulatory, speech-synthesis-by-rules.
Gnuspeech is an extensible, text-to-speech package, based on real-time, articulatory, speech-synthesis-by-rules. That is, it converts text strings into phonetic descriptions, aided by a pronouncing dictionary, letter-to-sound rules, rhythm and intonation models; transforms the phonetic descriptions into parameters for a low-level articulatory synthesiser; and uses these to drive an articulatory model of the human vocal tract producing an output suitable for the normal sound output devices used by GNU/Linux. The synthesiser is a tube resonance, or waveguide model that accurately models the behaviour of the real vocal tract. The associated modules are those used to develop the original spoken English databases, and they could be used for other languages. The whole software suite is suitable for psycho-acoustic and linguistic research.
