Self-Adjustable Neural Network for speech recognition

Neural networks with fixed input length are not able to train and test data with variable lengths in one network size. This issue is very crucial when the neural networks need to deal with signals of variable lengths, such as speech. Though various methods have been proposed in segmentation and feat...

Full description

Saved in:
Bibliographic Details
Published in:Engineering applications of artificial intelligence 2013-10, Vol.26 (9), p.2022-2027
Main Authors: Ting, Hua-Nong, Yong, Boon-Fei, Mirhassani, Seyed Mostafa
Format: Article
Language:English
Subjects:
Artificial intelligence
Children speech
Isolated words
Malay vowels
Neural Network
TIMIT
Variable input length
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural networks with fixed input length are not able to train and test data with variable lengths in one network size. This issue is very crucial when the neural networks need to deal with signals of variable lengths, such as speech. Though various methods have been proposed in segmentation and feature extraction to deal with variable lengths of the data, the size of the input data to the neural networks still has to be fixed. A novel Self-Adjustable Neural Network (SANN) is presented in this paper, to enable the network to adjust itself according to different data input sizes. The proposed method is applied to the speech recognition of Malay vowels and TIMIT isolated words. SANN is benchmarked against the standard and state-of-the-art recogniser, Hidden Markov Model (HMM). The results showed that SANN was better than HMM in recognizing the Malay vowels. However, HMM outperformed SANN in recognising the TIMIT isolated words.
ISSN:0952-1976
1873-6769
DOI:10.1016/j.engappai.2013.06.004