| software | tutorials | links |
|
|
|
|
| KPE (Klatt Parmater Editor) | The KPE80 program provides a graphical interface for the implementation of the Klatt 1980 formant synthesiser. The interface allows users to display and edit Klatt parameters using a graphical display which includes the time-amplitude waveform of both the original speech and its synthetic copy, and some signal analysis facilities. | Unix |
| Trackdraw | TRACKDRAW is a graphical interface for controlling the parameters of a speech synthesizer. | Matlab |
| CSLU Toolkit | The CSLU Toolkit was created to provide the basic framework and tools for people to build, investigate and use interactive language systems. These systems incorporate leading-edge speech recognition, natural language understanding, speech synthesis and facial animation. | Windows 95/98/NT |
| Speech Surfer | Speech Surfer is a tool for doing speech analysis and multi-modal speech synthesis. The analysis features include real time spectrograms and pitch extraction. The synthesis part include full parametric control of the KTH talking head and a formant synthesizer. The Speech Surfer tool, built on top of the Snack speech visualization module, is highly modular and extensible at several levels. It has multiple workareas which can be configured to display and edit general parameter trajectories and ,transcriptions. | Windows 95/98, IRIX, Solaris, HPUX, Linux, |
| Praat | A system for doing phonetics by computer.
The computer program Praat is a research, publication, and productivity
tool for phoneticians. With it, you can analyse,
synthesize, and manipulate speech, and create high-quality pictures for your articles and thesis. |
any platform |
| see also:
Software presented at the elsnet Eurospeech '99 Education Arena |
|
|
|
| Demonstration
of the TTS-System,
Selection of the Speech Units |
2 interactive tutorials. The first one displays the steps that are carried out in a TTS system based on a random text. The second one lets you interactivelly cut your own diphones and listen to synthestic speech based on these diphones. |
| Human Speech Production Based on a Linear Predictive Vocoder | The excitation and articulation, are realised (simulated) by a technical system, known as Linear Predictive Vocoder (LPC vocoder). Its principle and analogy to the human speech organs is explained. The main emphasis is put on the control parameters of the system - above all the pitch frequency and the vocal tract parameters (prediction coefficients) and the effect when they are manipulated. These manipulations are visually presented as changes of the time signal, pitch sequence and the spectrum and they are also audible. |
| see also:
Tutorials presented at the elsnet Eurospeech '99 Education Arena |
|
|
|
| Klatt Audio Scribe Notes for EE225d (other link) | The Audio clips of synthetic speech illustrating the history of the art and technology of synthetically produced human speech taken from Dennis H. Klatt's famous paper "Review of text-to-speech vonversion for English" JASA 82(3), 737-793, 1987 |
| Examples of synthesized speech | A collection of text-to-speech systems with sound examples (with a special emphasis on German systems) |
| Joseph P. Olive : "The Talking Computer": Text to Speech Synthesis (in: Hal's Legacy, MITPress) | Useful introduction to Text-to-Speech synthesis with further links (online version of the book). |
| German
TTS-systems -
synthesized emotional speech |
pages by Felix Burkhardt |