Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1016/j.engappai.2013.06.004 | Eng. Appl. of AI |
Keywords | Field | DocType |
speech recognition,input data,network size,neural network,malay vowel,self-adjustable neural network,test data,different data input size,variable length,fixed input length | Network size,TIMIT,Computer science,Segmentation,Speech recognition,Feature extraction,Time delay neural network,Test data,Artificial intelligence,Artificial neural network,Hidden Markov model,Machine learning | Journal |
Volume | Issue | ISSN |
26 | 9 | 0952-1976 |
Citations | PageRank | References |
2 | 0.38 | 16 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hua-Nong Ting | 1 | 6 | 2.49 |
Boon-Fei Yong | 2 | 2 | 0.38 |
Seyed Mostafa Mirhassani | 3 | 3 | 1.77 |