Title :
An optimal learning method for minimizing spotting errors
Author :
Komori, Takashi ; Katagiri, Shigeru
Author_Institution :
ATR Auditory & Visual Perception Res. Lab., Soraku-gun, Kyoto, Japan
Abstract :
A novel design method for word spotting, called MSPE (minimum spotting error), is proposed which guarantees a minimum spotting error situation in a probabilistic sense through MCE/GPD (minimum classification error/generalized probabilistic descent) optimization. MPSE makes it possible to train all trainable parameters consistently; this feature implies an innovative departure from conventional, heuristic approaches to spotter design. Experimental results have demonstrated a very high utilization potential for MSPE.<>
Keywords :
errors; learning (artificial intelligence); minimisation; neural nets; speech recognition; generalized probabilistic descent; minimum spotting error; optimal learning method; trainable parameters; utilization potential; word spotting;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference on
Conference_Location :
Minneapolis, MN, USA
Print_ISBN :
0-7803-7402-9
DOI :
10.1109/ICASSP.1993.319288
