Automatic Speech Recognition:

You are here: Courses / Tutorials / Software / Home

On-line Courses and Educational Material Relevant to Speech Recognition

Below is a list of links to courses offered within ISIP related to the area of human language technology, as well as links to some valuable on-line courses that are available on the Internet. Please submit your suggestions for other useful links to ies_help@cavs.msstate.edu.

Speech	MLearn	Stats	DSP	Other
Ext: Speech	Ext: MLearn	Ext: Stats	Ext: DSP	Ext: Other

ISIP On-line Courses:

Speech:

ECE 8483 - Fundamentals of Speech Recognition: The goal of this course is to develop a working knowledge of large vocabulary conversational speech recognition, including theory and practice.
ISIP 0000 - Fundamentals of Speech Recognition: This is a half-week short course on hidden Markov model approaches to speech recognition.
ECE 7000 - Special Topics in Speech Recognition: A series of one-hour seminars on current topics in speech recognition.
ASE 6713 - Introduction to Acoustics: A three-hour overview of the role of acoustics in speech processing.

Machine Learning:

ECE 8443 - Pattern Recognition: The foundations of speech recognition are based on fundamental machine learning topics such as classification and discrimination.

Statistics:

ECE 8990 - Information Theory: This course focuses on the principles of statistical modeling and characterization of data.

Digital Signal Processing:

ECE 4773 - Digital Signal Processing: An introductory course on representation of analog signals using discrete mathematics.
ECE 4000 - Special Topics in Signal Processing: A collection of senior-year projects performed by students interested in signal processing.
ECE 3813 - Signals and Systems: An entry-level course on the fundamentals of linear system theory.

Other:

ECE 2991 - Unix Software Tools: This special topics course was taught in 1995. It is fun to look back and observe the state of computing at that time.
ISIP 0001 - Unix Software Engineering: A special topics course describing Unix tools to support software engineering that was taught at Mtel (became Skytel... became WorldCom... became bankrupt...).

Related Internet-based Material:

Speech:

AESL: the LDC American English spoken lexicon.
BeRP: the Berkeley restaurant project.
comp.speech: resources at Cambridge University.
Debugging Tools: debugging tools for dynamic storage allocation and memory management.
Edinburgh Speech Tools Library: speech and linguistic classes and DSP algorithms.
EMU: Unix and Windows speech annotation system.
Entropic's HAPI: speech recognition engine.
The Intarc Communication Environment: message-passing subsystem for large distributed AI systems.
The Interference Progression Planner: ADL planning system.
The Jupiter Project: MIT's spoken language systems lab.
An Empirical Study of Smoothing Techniques for Language Modeling: information about language model smoothing by Stanley F. Chen and Joshua Goodman.
Language and Statistics: a course on language and statistics at CMU.
Linguistic Annotation: tools and formats for creating and managing linguistic annotations.
LPC: linear-predictive coding software.
Maximum Entropy: knowledge from incomplete information, without making unsubstantiated assumptions.
Modern Language Association of America (MLA): not-for-profit membership organization that promotes the study and teaching of language and literature.
recogviz: visualizing the speech recognition process.
SAPI v4.0 SDK: speech application programming interface for Microsoft Windows.
SNACK: speech visualization module.
Speech Technology Network: a virtual community for speech technology professionals.
SPIDER: natural language system (this site is in German).
STRUT: speech training and recognition unified tool.
Technovoice: click "Demo" to try the Eloquens(R), Actor(tm), and Flexus(R) speech generation systems (this site is in Italian).

Machine Learning:

The Basic Learning Model: designing a learning system.
Bayesian Belief Nets: list of applications.
FSM: finite state machine transducers.
Graphical Models: a brief introduction to graphical models and Bayesian networks.
JavaBayes: Bayesian networks in Java.
NICO toolkit: artificial neural network toolkit.
Pattern Recognition for HCI: an overview of pattern recognition and classification by R.O. Duda.
SVM Applets: pattern recognition and regression estimation.

Statistics:

AutoFit: automatic regression equation builder.
Basic Statistics: an online textbook from StatSoft, Inc.

Digital Signal Processing:

Auditory Toolbox: auditory models developed using Matlab.
B-DASUR1: contour recognition system.
Blitz++: FFT implementation using template meta-programming.
comp.dsp: frequently asked questions regarding comp.dsp.
dspGuru: the net's best single source of information and software for digital signal processing.
FIR filter design: summation of freely available FIR filter design software.
Image Classification: Berkeley digital library project.
Matlab: compatible matrix tool box in C++.
Mathtools: The technical computing portal for all your scientific and engineering needs.
Ptolemy 0.7.1: adaptive computing systems software.
White Mountain DSP, Inc.: DSP starter kits.
Introduction to DSP: an online DSP course at Bores Signal Processing.
Matlab: the official home page at Mathworks.
Matlab starter examples: a suite of example code for beginners.
Minimum Description Length Models: a review of coding schemes.
Techonline: a great resource for technical information about DSP.

Other:

ATSPD: dictionary of algorithms, data structures, and problems.
Concurrent Versions Systems: manual for CVS 1.9 by Per Cederqvist et al.
CVS resources: FAQ, reference manual, tutorial and links about CVS.
CVS information: from the Laboratory of Nuclear Sciences at Cornell University.
CVS tutorial: another tutorial, from the LNS at Cornell.
GNU make: manual edition 0.51 for make version 3.76 beta.
MySQL: public domain relational database system.
Shareware.com: software resources with a database of more than 250,000 files.
Solaris Numerical Computation Guide: a document explaining IEEE floating point operations and how they are implemented under Solaris.
Sun Documentation: manuals, guides, answer books, and manual pages.
WAVE File Format: description of the WAVE file format.
wget: web spider/capture.
Wotsit's Format: the complete programmer's resource on the net for file formats.

Help / Support / Site Map / Contact Us / ISIP Home