TY - CHAP
T1 - Application of EalphaNets to Feature Recognition of Articulation Manner in Knowledge-Based Automatic Speech Recognition
AU - Vassallo, Giorgio
AU - Gentile, Antonio
AU - Sorbello, Filippo
AU - Siniscalchi, Sabato Marco
AU - Siniscalchi, Sabato M.
AU - Clements, Mark A.
AU - Li, Jinyu
AU - Pilato, Giovanni
PY - 2006
Y1 - 2006
N2 - Speech recognition has become common in many application domains. Incorporating acoustic-phonetic knowledge into Automatic Speech Recognition (ASR) systems design has been proven a viable approach to rise 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, a set of six detectors for the above mentioned attributes is designed based on the E-αNet model of neural networks. This model was chosen for its capability to learn hidden activation functions that results in better generalization properties. Experimental set-up and results are presented that show an average 3.5% improvement over a baseline neural network implementation
AB - Speech recognition has become common in many application domains. Incorporating acoustic-phonetic knowledge into Automatic Speech Recognition (ASR) systems design has been proven a viable approach to rise 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, a set of six detectors for the above mentioned attributes is designed based on the E-αNet model of neural networks. This model was chosen for its capability to learn hidden activation functions that results in better generalization properties. Experimental set-up and results are presented that show an average 3.5% improvement over a baseline neural network implementation
KW - Anthropomorphic robots
KW - Robots
KW - cognitive architecture
KW - Anthropomorphic robots
KW - Robots
KW - cognitive architecture
UR - http://hdl.handle.net/10447/59647
M3 - Chapter
SN - 3540331832
T3 - LECTURE NOTES IN COMPUTER SCIENCE
SP - 140
EP - 146
BT - Lecture Notes in Computer Science
ER -