One of the difficult problems of acoustic modeling for Automatic Speech Recognition (ASR) is how to adequately model the wide variety of acoustic conditions which may be present i...
Abstract--We describe some high-level approaches to estimating confidence scores for the words output by a speech recognizer. By "high-level" we mean that the proposed me...
Existing large-scale articulatory databases describe the tongue shape through the 2D positions of 3–4 fixed landmarks on the tongue surface. The ability to reconstruct the full...
Abstract. Real-time systems usually encompass parts that are best described by a continuous-time model, such as physical processes under control, together with other components tha...
This paper concerns both rhythm recognition and tempo analysis of expressive music performance based on a probabilistic approach. In rhythm recognition, the modern continuous spee...