This study deals with acoustic phonetic modelling in HMM based continuous speech recognition. Context dependent phone models were derived by a decision tree clustering algorithm. In particular, lexical stress was introduced as a clustering variable in addition to the phonetic context. The parameter sharing model was extended by tying HMM states across different target phones. For instance, one ...

OBJECTIVE The aim was to determine whether the ability to use place-coded vowel formant information could be improved after training in a group of congenitally deafened patients, who showed limited speech perception ability after cochlear implant use ranging from 1 yr 8 mo to 6 yr 11 mo. A further aim was to investigate the relationship between electrode position difference limens and vowel rec...

The present study investigated whether moderate amounts of computer-assisted speech training can improve the speech recognition performance of hearing-impaired children. Ten Mandarin-speaking children (3 hearing aid users and 7 cochlear implant users) participated in the study. Training was conducted at home using a personal computer for half an hour per day, 5 days per week, for a period of 10...

Differences in human vocal tract lengths can cause inter speaker acoustic variability in speech signals spoken by different speakers for the same textual version and due to these variations, the robustness of a speaker independent (SI) speech recognition system is affected. Speaker normalization using vocal tract length normalization (VTLN) is an effective approach to reduce the affect of these...

The literature on vowel perception contains contradictory claims concerning the use of information from the consonant-vowel and vowel-consonant transitions in vowel recognition. Some studies claim to have found that listeners use vowel formant track shape to compensate for changes in production brought about by coarticulation. Others claim that no evidence for such a compensation could be found...

The literature on vowel perception contains contradictory claims concerning the use of information from the consonant-vowel and vowel-consonant transitions in vowel recognition. Some studies claim to have found that listeners use formant track shape to compensate for changes in production brought about by coarticulation. Others claim that no evidence for such a compensation could be found. Our ...

Current understanding of disability and impairment has led to new approaches in Rehabilitation. In this issue of Iranian Rehabilitation Journal, a variety of articles introduces a new trend in rehabilitation. "Emotion pitch" of each vowel sound and Percentage of vowel correct is the subject which Talie Zarifian and her colleagues discussed in their article. Persian speaking children can get ben...

This paper discusses a new approach to improve tone recognition by modeling the tone nucleus with vowel landmark detection. The tone nucleus region is identified based on vowel landmark frames derived by an automatic landmark recognition system. In the corresponding tone recognition experiments, the best results with landmark-based tone nucleus regions outperform the best baseline system result...