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 is 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 segmentation errors.
Bibliographic reference. Hübener, Kai (1995): "Using segmental coefficients in HMM speech recognition", In EUROSPEECH-1995, 935-938.