4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Using Multi-Level Segmentation Coefficients to Improve HMM Speech Recognition

Kai Hübener

University of Hamburg, Computer Science Dept., Germany

This paper presents a new kind of acoustic features for HMM speech recognition. These features try to capture phone-specific segmentation information using multiple temporal resolutions. Experiments show that word accuracy can be improved by 7% when combining these features with traditional mel-cepstral coefficients in a speaker-independent word recogniser. This improvement is mostly due to a reduced number of insertion and deletion errors.

Full Paper

Bibliographic reference.  Hübener, Kai (1996): "Using multi-level segmentation coefficients to improve HMM speech recognition", In ICSLP-1996, 248-251.