A study on the new hybrid recurrent TDNN - HMM architecture for speech recognition


The KIPS Transactions:PartB , Vol. 8, No. 6, pp. 699-704, Dec. 2001
10.3745/KIPSTB.2001.8.6.699,   PDF Download:

Abstract

In this paper, a new hybrid modular recurrent TDNN (time-delay neural network)-HMM (hidden Markov model) architecture for speech recognition has been studied. In TDNN, the recognition rate could be increased if the signal window is extended. To obtain this effect in the neural network, a high-level memory generated through a feedback within the first hidden layer of the neural network unit has been used. To increase the ability to deal with the temporal structure of phonemic features, the input layer of the network has been divided into multiple states in time sequence and has feature detector for each states. To expand the network from small recognition task to the full speech recognition system, modular construction method has been also used. Furthermore, the neural network and HMM are integrated by feeding output vectors from the neural network to HMM, and a new parameter smoothing method which can be applied to this hybrid system has been suggested.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
C. S. Jang, "A study on the new hybrid recurrent TDNN - HMM architecture for speech recognition," The KIPS Transactions:PartB , vol. 8, no. 6, pp. 699-704, 2001. DOI: 10.3745/KIPSTB.2001.8.6.699.

[ACM Style]
Choon Seo Jang. 2001. A study on the new hybrid recurrent TDNN - HMM architecture for speech recognition. The KIPS Transactions:PartB , 8, 6, (2001), 699-704. DOI: 10.3745/KIPSTB.2001.8.6.699.