CMU Artificial Intelligence Repository
Home INFO Search FAQs Repository Root

Klatt: A Klatt-style speech synthesizer implemented in C.

areas/speech/systems/klatt/
This directory contains a C implementation of a Klatt-style cascade parallel formant speech synthesizer. The software is an attempt to implement, and remain faithful to, Dennis Klatt's original design of software synthesizer, as described in the original JASA article. The aim of the software is to convert frames of audio parameters into chunks of speech waveform. Forty parameters are specified per frame, including formant frequencies, amplitudes and bandwidths, voicing, frication and so on. Each frame of parameters usually represents 10ms of output speech. Two (simple!) example parameter files are supplied with the package.
Origin:   

   ftp.cs.bham.ac.uk:/pub/dist/synth/sources/
   svr-ftp.eng.cam.ac.uk:/pub/comp.speech/sources/
   as the file klatt.3.0.4.tar.Z

Version: 3.0.4 (9-MAY-94) Requires: C Copying: GNU GPL v1 CD-ROM: Prime Time Freeware for AI, Issue 1-1 Author(s): Jon Iles Nick Ing-Simmons Contact: Jon Iles School of Computer Science University of Birmingham Birmingham, B15 2TT. UK Tel: +44(0)21-414-3736 Keywords: Authors!Iles, Authors!Ing-Simmons, C!Code, Formant Synthesis, GNU GPL, Klatt, Speech Synthesis References: Dennis H. Klatt, "Software for a cascade/parallel formant synthesizer", Journal of the Acoustic Society of America 67(3):971-995, March 1980. D.H. Klatt and L.C. Klatt, "Analysis, synthesis and perception of voice quality variations among female and male talkers", Journal of the Acoustical Society of America, 87(2):820-857, February 1990.
Last Web update on Mon Feb 13 10:28:27 1995
AI.Repository@cs.cmu.edu