论文信息 - A dynamic neural network for syllable recognition

A dynamic neural network for syllable recognition

A dynamic neural network architecture based on the time-delay neural network and the convolutional neural network is originated. The dynamic network achieves much better performance than those of MLP and TDNN when dealing with syllable recognition. Such performance is also comparable to that of the more popular HMM method.

Lin Zhong | Runsheng Liu | Yuanyuan Shi

[1] Kiyohiro Shikano,et al. Modularity and scaling in large phonemic neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[2] I. Guyon,et al. Handwritten digit recognition: applications of neural network chips and automatic learning , 1989, IEEE Communications Magazine.

[3] Lin-Shan Lee,et al. Continuous hidden Markov models integrating transitional and instantaneous features for Mandarin syllable recognition , 1993, Comput. Speech Lang..

[4] Gee-Swee Poo. Large vocabulary Mandarin Final recognition based on Two-Level Time-Delay Neural Networks (TLTDNN) , 1997, Speech Commun..

[5] Le CunY.,et al. Handwritten digit recognition , 1989 .

[6] Geoffrey E. Hinton,et al. A time-delay neural network architecture for isolated word recognition , 1990, Neural Networks.

[7] Geoffrey E. Hinton,et al. Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..