Automatic Speech Recognition: The Development of the Sphinx Recognition System
Automatic Speech Recognition: The Development of the Sphinx Recognition System
Improvements and applications for key word recognition using hidden Markov modeling techniques
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
| Hi-index | 0.00 |
In this paper we describe a technique for nonkeyword rejection and we will evaluate in the context of an audiotex service using the ten Spanish digits. The baseline keyword recognition system is a speaker-independent continuous density Hidden Markov Model recognizer. We propose the use of an affine transformation to the log-probability of the garbage model, an HMM model trained to account for both nonkeyword speech and non-stationary telephone noises. The parameters of the transformation for the case of isolated keywords are chosen to minimize a cost function that weighs the keyword error rate, keyword rejection rate and false acceptance rate according to the a priori probabilities of keyword/non-keyword and the requirements of the specific application. This technique was also extended to embedded keywords (word-spotting). Use of this rejection technique on the audiotex application reduced the total cost function up to 20% for isolated-word case and 12% for the word-spotting case.