Title :
Keyword spotting based on recurrent neural network
Author :
Jianlai, Zhou ; Jian, Liu ; Yantao, Song ; Tiecheng, Yu
Author_Institution :
Acad. Sinica, Beijing, China
Abstract :
In this paper, a recognition method is proposed which has been applied to KWS (keyword spotting) and based on a recurrent neural network. The proposed recurrent neural network has memory within a several time steps´ interval, and its classification ability is more powerful than the HMM (hidden Markov models). It can process a time sequence signal and shows some interesting properties in performing time warping. The RTRL (real time recurrent learning) algorithm is used to train the neural network. Two numerical examples are presented to demonstrate the merit of the neural network. Finally, we look at the defects of the scheme, and discuss strategies for combining this approach with HMM in order to decide the time position of KWS by in a more precise manner
Keywords :
hidden Markov models; learning (artificial intelligence); recurrent neural nets; speech recognition; HMM; KWS; hidden Markov models; keyword spotting; real time recurrent learning; recognition method; recurrent neural network; speech recognition; time sequence signal; Acoustics; Artificial neural networks; Delay effects; Electronic mail; Hidden Markov models; Neural networks; Neurons; Recurrent neural networks; Signal processing; Speech recognition;
Conference_Titel :
Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-4325-5
DOI :
10.1109/ICOSP.1998.770310