Bi-directional phonetic modeling of consonant-vowel speech patterns

• Main Authors: Huang, Guangpu, Er, Meng Joo
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2013
• Online Access: https://hdl.handle.net/10356/99005; http://hdl.handle.net/10220/12845
• Institution: Nanyang Technological University

This paper studies the dual aspects of speech recognition and synthesis using the consonant-vowel speech patterns. It examines the feasibility of bi-directional phonetic modeling, i.e., articulatory encoding and auditory decoding, in a neural based computational model supplemented with an interactive learning algorithm. Simulation results demonstrate that the proposed method offers a simple yet elegant solution for improved phonetic representation. This work serves to offer a collective and unified explanation for the dynamic nature of English speech, which holds great potential for future developments of human-like speech processing systems.