Title :
Subspace Gaussian mixture model for computer-assisted language learning
Author :
Rong Tong ; Boon Pang Lim ; Chen, Nancy F. ; Bin Ma ; Haizhou Li
Author_Institution :
Inst. for Infocomm Res., Singapore, Singapore
Abstract :
In computer-assisted language learning (CALL), speech data from non-native speakers are usually insufficient for acoustic modeling. Subspace Gaussian Mixture Models (SGMM) have been effective in training automatic speech recognition (ASR) systems with limited amounts of training data. Therefore, in this work, we propose to use SGMM to improve the fluency assessment performance. In particular, the contributions of this work are: (i) The proposed SGMM acoustic model trained with native data outperforms the MMI-GMM/HMM baseline by 25% relative, (ii) when incorporating a small amount of non-native training data, the SGMM acoustic model further improves the performance of fluency assessment by 47% relative.
Keywords :
Gaussian processes; acoustic signal processing; computer aided instruction; linguistics; mixture models; natural language processing; speech recognition; ASR systems; CALL; SGMM acoustic modeling; automatic speech recognition; computer-assisted language learning; fluency assessment performance; nonnative speakers; nonnative training data; speech data; subspace Gaussian mixture models; Acoustics; Correlation; Data models; Hidden Markov models; Speech; Speech recognition; Training; Automatic Speech Recognition (ASR); Computer Assisted Language Learning (CALL); Fluency assessment; Goodness Of Pronunciation (GOP); Subspace Gaussian Mixture Model (SGMM);
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
Conference_Location :
Florence
DOI :
10.1109/ICASSP.2014.6854624