Articulatory speech synthesis
1. Why articulatory speech synthesis?
Modern personal computers have gigabytes of RAM and hundreds or thousands of gigabytes of storage space. This allowed concatenative speech synthesizers with very big databases (hundreds of megabytes), which are able to produce very high quality speech. And the new synthesizers based on deep neural networks (DNN) are producing speech with excellent quality. But these methods depend on recorded speech. To create a new high quality voice, many hours of speech must be recorded.
Articulatory synthesis is a method that produces speech by simulating the human phonatory system. For this reason, it is possible to develop an articulatory synthesizer that does not depend on recorded speech. Producing high quality speech with articulatory synthesizers is very difficult, but it is relatively easy to change their voice, for example from male to female. The user just needs to modify some parameters.
The most interesting characteristic of articulatory synthesizers is that they do not treat the phonatory system as a black box. For example, with articulatory synthesizers we can easily understand the cause of the differences between the "ba" and "ma" sounds (the velum aperture), or between "ba" and "da" (the constriction position).
The video "Real-time control of an articulatory speech synthesizer" demonstrates the flexibility of articulatory synthesizers. The speech quality is not good, but the video shows the potential of articulatory synthesis.
Articulatory vocal tract synthesis in
It is an open source software.
GamaTTS is an experimental articulatory speech synthesizer, derived from Gnuspeech. It is an open source software.
Gnuspeech is still the only articulatory text-to-speech system (apart from derived projects). It is an open source software.
Pink Trombone is a web vocal tract simulator. It is an open source software.
Praat contains a vocal tract simulation. The vocal tract model in Praat was developed to synthesize sounds that other implementations were not able to produce. It is an open source software.
MATLAB realtime/interactive tools for speech science research and education. It is an open source software.
CWEB port of Pink Trombone. It is an open source software.
VocalTractLab is a software for articulatory synthesis research that uses a 3d geometry model of the phonatory system. It produces high quality speech and is an open source software.
Vocal tract modelling with the 2D digital
The software is closed source, but may be used free of charge.
This is a MATLAB implementation of the vocal tract model by Dr. Shinji Maeda. The source code is available.
VTDemo is a vocal tract simulator. The vocal tract model is based on VTCalcs. It is a closed source software, but may be used free of charge.