论文信息 - Recognition of Assamese Phonemes Using RNN Based Recognizer

Recognition of Assamese Phonemes Using RNN Based Recognizer

This paper discusses a novel technique for the recognition of Assamese phonemes using Recurrent Neural Network (RNN) based phoneme recognizer. A Multi-Layer Perceptron (MLP) has been used as phoneme segmenter for the segmentation of phonemes from isolated Assamese words. Two different RNN based approaches have been considered for recognition of the phonemes and their performances have been evaluated. MFCC has been used as the feature vector for both segmentation and recognition. With RNN based phoneme recognizer, a recognition accuracy of 91% has been achieved. The RNN based phoneme recognizer has been tested for speaker mismatched and channel mismatched conditions. It has been observed that the recognizer is robust to any unseen speaker. However, its performance degrades in channel mismatch condition. Cepstral Mean Normalization (CMN) has been used to overcome the problem of performance degradation effectively.

Utpal Bhattacharjee

[1] Ronald J. Williams,et al. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[2] Gwilym M. Jenkins,et al. Time series analysis, forecasting and control , 1972 .

[3] Utpal Bhattacharjee. Search Key Identification in a Spoken Query using Isolated Keyword Recognition , 2010 .

[4] Tuan Van Pham,et al. DWT-based phonetic groups classification using neural networks , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[5] Choochart Haruechaiyasak,et al. Thai Word Recognition Using Hybrid MLP-HMM , 2010 .

[6] C. Weinstein,et al. A system for acoustic-phonetic analysis of continuous speech , 1975 .

[7] V.W. Zue,et al. The use of speech knowledge in automatic speech recognition , 1985, Proceedings of the IEEE.

[8] Erol Gelenbe,et al. Neural Networks: Advances and Applications II , 1991 .

[9] J. Makhoul,et al. Where the phonemes are: Dealing with ambiguity in acoustic-phonetic recognition , 1975 .

[10] Dominique Fohr,et al. Continuous speech segmentation with the gamma memory model , 1995, EUROSPEECH.

[11] Youngjik Lee,et al. Phoneme segmentation of continuous speech using multi-layer perceptron , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.