CMU Artificial Intelligence Repository
Home INFO Search FAQs Repository Root

OGI Speech Tools: Speech data manipulation tools

This directory contains the OGI Speech Tools, a set of speech data manipulation tools developed at the Center for Spoken Language Understanding (CSLU) at the Oregon Graduate Institute of Science and Technology (Portland Oregon). The tools can be used to compute and display signal representations, label speech at different levels (e.g., phonetic, phonemic and word), train neural network classifiers, and display the output of classification or recognition algorithms time-aligned with the speech. The distribution includes, among other things, + LYRI, an X Windows tool for displaying data in a time synchronous fashion (speech signal, spectrograms, phoneme labels). + NOPT, a neural network training package, which uses Conjugate Gradient descent optimization. + LIBNSPEECH, an extensive set of C library signal processing routines for the manipulation of speech data, including PLP Analysis, Rasta PLP Analysis, Linear Predictive Coding, Mel Cepstrum Coding, and Fast Fourier Transform. + Utilities for converting file formats, such as ADC to NIST, to/from mu-law, filtering the speech waveform, and ascii/binary data streams. + A Vector-Quantizer based on the Linde Buzo and Gray (LBG) algorithm.

Version: 1.0 (20-OCT-93) Requires: ANSI C Ports: Sun4, DECStation (Ultrix), RS6000 (AIX), HPPA-RISC (HPUX 8.0) CD-ROM: Prime Time Freeware for AI, Issue 1-1 Mailing List: To join the mailing list for notification of additions and changes, send mail to Author(s): Mark Fanty, Johan Schalkwyk, Yeshwant Muthusamy, Ron Cole, Etienne Barnard, Fill Aleva, John Pochmara, Malcom Slaney, Delemar Olivier Contact: Johan Schalkwyk Center for Spoken Language Understanding Oregon Graduate Institute Keywords: Authors!Aleva, Authors!Barnard, Authors!Cole, Authors!Fanty, Authors!Muthusamy, Authors!Olivier, Authors!Pochmara, Authors!Schalkwyk, Authors!Slaney, C!Code, CSLU, Conjugate Gradient Descent Optimization, FFT, Fast Fourier Transform, LIBNSPEECH, LYRI, Linear Predictive Coding, Mel Cepstrum Coding, Mu-law, NOP, Neural Networks, OGI Speech Tools, PLP Analysis, Rasta PLP Analysis, Spectrograms, Speech Processing, Speech Recognition, Vector Quantization References: ?
Last Web update on Mon Feb 13 10:28:29 1995