Department of Special Education and Communication Disorders
Department of Special Education and Communication Disorders: Faculty Publications
Document Type
Article
Date of this Version
9-13-2012
Citation
Proceedings, Interspeech 2012 : ISCA 13th Annual Conference (September 9-13, 2012 : Portland, Oregon), pages 1,327-1,330
doi: 10.21437/Interspeech.2012-318
International Speech Communication Association
Abstract
Articulation-based silent speech interfaces convert silently produced speech movements into audible words. These systems are still in their experimental stages, but have significant potential for facilitating oral communication in persons with laryngectomy or speech impairments. In this paper, we report the result of a novel, real-time algorithm that recognizes whole-words based on articulatory movements. This approach differs from prior work that has focused primarily on phoneme-level recognition based on articulatory features. On average, our algorithm missed 1.93 words in a sequence of twenty-five words with an average latency of 0.79 seconds for each word prediction using a data set of 5,500 isolated word samples collected from ten speakers. The results demonstrate the effectiveness of our approach and its potential for building a real-time articulation-based silent speech interface for health applications.
Included in
Computer Sciences Commons, Speech and Hearing Science Commons, Systems and Integrative Engineering Commons
Comments
Copyright 2012, Wang, Samal, Green, and Rudzicz. Used by permission