Linking Cognitive Tokens to Biological Signals: Dialogue Context Improves Neural Speech Recognizer Performance
Year: 2013
Type: article
Abstract: This paper presents a hybrid cognitive model engaged in experiments demonstrating a successful mechanism for applying top-down contextual bias to a neural speech recognition system to improve its performance.The hybrid model includes a model of social dialogue moves, which it uses to selectively bias word recognition probabilities at a low level in the neural speech recognition system.The model demonstrates how symbolic and neurologically inspired components can successfully exchange information and mutually influence their processing.Furthermore, the biasing mechanism is grounded in brain mechanisms of perceptual decision making.
Authors: Richard Veale, Gordon Briggs, Matthias Scheutz
Institution: Indiana University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1249167578, G8876996369
OpenAlex ID: W2402436611