Making large-scale support vector machine learning practical
Advances in kernel methods
Structural event detection for rich transcription of speech
Structural event detection for rich transcription of speech
Hi-index | 0.00 |
The goal of speech event detection (SED) is to reveal the presence of important elements in the speech signal for different sound classes. In a speech recognition system, events can be combined to detect phones, words or sentences, or to identify landmarks with which a decoder could be synchronized. In this paper, we introduce three popular classification techniques, HMM, SVM, ANN and Non-Negative Matrix Deconvolution (NMD) for SED. The main purpose of this paper is to compare the performance of (1) HMM, (2) hybrid SVM/NMD (3) hybrid SVM/HMM and (4) hybrid MLP /HMM approaches to SED and emphasize approaches to reaching lower Event Error Rates (EER). It was found that the hybrid SVM/HMM approach outperformed the HMM system. Regarding EER, an improvement of 6% was achieved. The hybrid MLP/HMM got the best EER rate. Improvements of 11% and 8% were found in comparison with the HMM and hybrid SVM/HMM event detector, respectively.