Embedded Knowledge-Based Speech Detectors for Real-Time Recognition Tasks

Speech recognition has become common in many application domains, from dictation systems for professional practices to vocal user interfaces for people with disabilities or hands-free system control. However, so far the performance of Automatic Speech Recognition (ASR) systems are comparable to Human Speech Recognition (HSR) only under very strict working conditions, and in general much lower. Incorporating acoustic-phonetic knowledge into ASR design has been proven a viable approach to raise ASR accuracy. Manner of articulation attributes such as vowel, stop, fricative, approximant, nasal, and silence are examples of such knowledge. Neural networks have already been used successfully as detectors for manner of articulation attributes starting from representations of speech signal frames. In this paper the full system implementation is described. The system has a first stage for MFCC extraction followed by a second stage implementing a sinusoidal based multi-layer perceptron for speec...

• Type: Conference
• Year: 2006
• Where: ICPPW
• Authors: Sabato Marco Siniscalchi, Fulvio Gennaro, Salvatore Andolina, Salvatore Vitabile, Antonio Gentile, Filippo Sorbello
• Keywords: Articulation Attributes, Automatic Speech Recognition, Distributed And Parallel Computing, ICPPW 2006, Speech Recognition