Table 2.
Comparison of the classification accuracy of the proposed SOM-SNN framework against other baseline frameworks on the TIDIGITS dataset.
| Model | Accuracy (%) |
|---|---|
| Single-layer SNN and SVM (Tavanaei and Maida, 2017a)a | 91.00 |
| Spiking CNN and HMM (Tavanaei and Maida, 2017b)a | 96.00 |
| AER Silicon Cochlea and SVM (Abdollahi and Liu, 2011)b | 95.58 |
| AER Silicon Cochlea and Deep RNN (Neil and Liu, 2016)b | 96.10 |
| AER Silicon Cochlea and Phased LSTM (Anumula et al., 2018)b | 91.25 |
| Liquid State Machine (Zhang et al., 2015)c | 92.30 |
| MFCC and GRU RNN (Anumula et al., 2018)c | 97.90 |
| SOM and SNN (this work)c | 97.40 |
a
Evaluate on the Aurora dataset which was developed from the TIDIGITS dataset.
b
The data was collected by playing the audio files from the TIDIGITS dataset to the AER Silicon Cochlea Sensor.
c
Evaluate on the TIDIGITS dataset.