Noisy Chinese Speech Recognition Based on Linear Prediction of One-sided Autocorrelation Sequence
Xinyu Huang · Acta Scicentiarum Naturalum Universitis Pekinesis · 2000
A new way is supplied to increase the recognition rate of Chinese speech in nois e.It includes two parts. One is using the autocorrelation function to detect the speech terminal, the other is using the coefficients based on the one\|sided au t ocorrelation sequence to replace the original speech signal and then extract the speech feature to recognize.Isolated word recognition experiment based on DTW s hows:it can reduce the disturbance of noise effectively and get the high recogni tion rate.It is of great advantage to apply when SNR (signal to noise rate) is l ow.