SAL Home OTHERS Artificial Intelligence


ISIP's public domain automatic speech recognition (ASR) system is a powerful large vocabulary conversational speech recognizer (LVCSR) that draws heavily from the diverse research areas of statistical pattern recognition, digital signal processing, artificial intelligence, linguistics, and information theory.

At present, the ISIP ASR system supports the following utilities and applications:

  • Acoustic feature extraction of mel-frequency cepstra and their temporal derivatives based on FFT as well as LP analysis.
  • Viterbi training of continuous density Hidden Markov Models (HMMs) with single Gaussian or mixture distributions for context independent as well as context-dependent acoustic models.
  • Efficient single-pass decoding using a hierarchical variation of Viterbi search.

Current Version:   alpha version

License Type:   ??

Home Site:

Source Code Availability:   Yes

Available Binary Packages:

  • Debian Package:   No
  • RedHat RPM Package:   No
  • Other Packages:   No

Targeted Platforms:

C++ platforms

Software/Hardware Requirements:

C++ compiler such as gcc

Other Links:

Mailing Lists/USENET News Groups:


User Comments:

  • None

See A Screen Shot? (Not Yet)

  SAL Home   |   Other Scientific Fields   |   Artificial Intelligence

Comments? SAL@KachinaTech.COM
Copyright © 1995-2001 by Herng-Jeng Jou
Copyright © 1997-2001 by Kachina Technologies, Inc.
All rights reserved.