Low cost speech detection using Haar-like filtering for sensornet
Jun Nishimura, Tadahiro Kuroda · 2008
Haar-like filtering based speech detection is proposed as a new and very low calculation cost method for sensornet applications. The simple haar-like filters having variable filter width and shift width are trained to learn appropriate filter parameters from the training samples to detect speech. Our method yielded speech/nonspeech classification accuracy of 96.93% for the input length of 0.1s. Compared with high performance feature extraction method MFCC (Mel-Frequency Cepstrum Coefficient), the proposed haar-like filtering can be approximately 85.77% efficient in terms of the amount of add and multiply calculations while capable of achieving the error rate of only 3.03% relative to MFCC.