Sixth European Conference on Speech Communication and Technology
(EUROSPEECH'99)

Budapest, Hungary
September 5-9, 1999

A Public Domain Speech-to-Text System

M. Ordowski (2), N. Deshmukh (1), A. Ganapathiraju (1), J. Hamaker (1), Joseph Picone (1)

(1) Institute for Signal and Information Processing, Department for Electrical and Computer Engineering, Mississippi State University, Mississippi State, MS, USA
(2) Department of Defense, Ft. Meade, MD, USA

The lack of freely available state-of-the-art Speech-to-Text (STT) software has been a major hindrance to the development of new audio information processing technology. The high cost of the infrastructure required to conduct state-of-the-art speech recognition research prevents many small research groups from evaluating new ideas on large-scale tasks. In this paper, we present the core components of an available state-of-the-art STT system: an acoustic processor which converts the speech signal into a sequence of feature vectors; a training module which estimates the parameters for a Hidden Markov Model; a linguistic processor which predicts the next word given a sequence of previously recognized words; and a search engine which finds the most probable word sequence given a set of feature vectors.


Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Ordowski, M. / Deshmukh, N. / Ganapathiraju, A. / Hamaker, J. / Picone, Joseph (1999): "A public domain speech-to-text system", In EUROSPEECH'99, 2127-2130.