LCS Publication Details
Publication Title:
Publication Author: ,
Additional Authors:
LCS Document Number: MIT-LCS-TR-752
Publication Date: 6-1-1998
LCS Group: Spoken Language Systems
Additional URL: No URL Given
Currently, most approaches to speech recognition are frame-based and represent speech as a temporal sequence of feature vectors. In contrast, a segment-based approach represents speech as a temporal graph of feature vectors and provides a more general fr
To obtain this publication:

To purchase a printed copy of this publication please contact MIT Document Services.