Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition

Details Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition

2007-11-06

arxiv.org/abs/0711.0811v1

Dans InterSpeech 2007 (2007)

Computer Science

Computation and Language

Scientific paper

In this paper, we present several adaptation methods for non-native speech recognition. We have tested pronunciation modelling, MLLR and MAP non-native pronunciation adaptation and HMM models retraining on the HIWIRE foreign accented English speech database. The ``phonetic confusion'' scheme we have developed consists in associating to each spoken phone several sequences of confused phones. In our experiments, we have used different combinations of acoustic models representing the canonical and the foreign pronunciations: spoken and native models, models adapted to the non-native accent with MAP and MLLR. The joint use of pronunciation modelling and acoustic adaptation led to further improvements in recognition accuracy. The best combination of the above mentioned techniques resulted in a relative word error reduction ranging from 46% to 71%.

Affiliated with

Also associated with

No associations

Rating

Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-134187