Title :
Using multi-level segmentation coefficients to improve HMM speech recognition
Author_Institution :
Dept. of Comput. Sci., Hamburg Univ., Germany
Abstract :
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
Keywords :
errors; feature extraction; hidden Markov models; speech recognition; HMM speech recognition; acoustic features; deletion errors; experiments; feature extraction; hidden Markov model; insertion errors; mel-cepstral coefficients; multi-level segmentation coefficients; multiple temporal resolutions; phone-specific segmentation information; speaker-independent word recogniser; word accuracy; Cepstral analysis; Computer science; Data mining; Feature extraction; Hidden Markov models; Humans; Robustness; Signal resolution; Speech recognition; Viterbi algorithm;
Conference_Titel :
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-7803-3555-4
DOI :
10.1109/ICSLP.1996.607091
