CMU Artificial Intelligence Repository
Home INFO Search FAQs Repository Root

Speech Recognition and Synthesis Software

areas/speech/systems/

   afsp/      AFsp: Audio File I/O Routines
   celp/      CELP: FS-1016 Code Excited Linear Prediction 
              coder
   cookbook/  Cookbook: Speech processing functions in C.
   eng2phon/  English to Phoneme Translation
   fview/     Fview: Speech trajectory analysis and display
   g7xx/      G711_G721_G723: CCITT ulaw and ADPCM compression 
              coders.
   gsm/       GSM: Implementation of the 13 kbps GSM speech 
              coding standard.
   hmm/       HMM: Hidden Markov Model software for automatic 
              speech recognition.
   klatt/     Klatt: A Klatt-style speech synthesizer 
              implemented in C.
   kplot/     KPlot: Simple graphical editor for Klatt 
              parameter files.
   ldcelp/    LD-CELP: Implementation of the Low-Delay Code 
              Excited Linear Prediction Speech Coding Standard
   lotec/     LOTEC: Simple Speech Recognition System
   lpc/       LPC-10: Implementation of DoD LPC-10 2400 bps 
              Voice Coder
   netaudio/  NetAudio: Audio protocol for networks
   ogitools/  OGI Speech Tools: Speech data manipulation tools
   pc_conv/   PC Convolution Demo: Graphic illustration of the 
              convolution operation
   pcm2alaw/  PCM to A-law: Convert from linear or u-law PCM to 
              and from A-law PCM
   pt/        Pitch Tracker: Pitch extractor and pitch period 
              marking program
   rasta/     Rasta: The RASTA-PLP front end for speech 
              recognition
   recnet/    RECNET: Connectionist speech recognition system 
              using recurrent nets.
   rplay/     RPLAY: Sound package with network audio
   rsynth/    RSYNTH: Complete speech synthesis system for UNIX
   shorten/   Shorten: A lossless compressor for waveform files
   sox/       SOX: Converts between various audio formats
   spasm/     SPASM: Perry Cook's Singing Voice Synthesizer
   spctools/  SPC Toolbox: Signal Processing and Communications
   speak/     SPEAK: Text to speech via phoneme concatenation.
   textnorm/  TEXTNORM: A very simple text normalization 
              package.
This directory contains speech recognition and speech synthesis software.
CD-ROM: Prime Time Freeware for AI, Issue 1-1 Keywords: Speech Recognition, Speech Synthesis
Last Web update on Mon Feb 13 10:28:38 1995
AI.Repository@cs.cmu.edu