We introduce a novel mechanism for incorporating articulatory dynamics into speech recognition with the theory of task dynamics.
Although modern automatic speech recognition (ASR) takes several cues from the biological perception of speech, it rarely models its biological production.
The use of theoretical (phonological) features of the vocal tract has provided some improvement over traditional acoustic ASR systems in phoneme recognition with neural networks (Kirchhoff, 1999; Roweis, 1999), but there has been very little work in ASR informed by direct measurements of the vocal tract.
We now turn to the task of speech recognition.
Our first experimental system attempts speech recognition given only articulatory data.
Our goal is to integrate task dynamics within an ASR system for continuous sentences called TD-ASR.
Experimental data is obtained from two sources, as described in section 2.2.
The articulatory medium of speech rarely informs modern speech recognition.
See all papers in Proc. ACL 2010 that mention baseline systems.
See all papers in Proc. ACL that mention baseline systems.
Back to top.