Abstract | ||
---|---|---|
The paper uses a new wavelet-Bark wavelet to meet critical frequency band division demand that is consistent with the perception of the human ear to the speech frequency. It is used in front-end processing of speech recognition system as filter bank instead of original FIR filter bank for improving the system performance. The paper gave the concept and parameter setting method of Bark wavelet. At the same time, the paper also presents an improved feature: CZCPA (Combining Zero-Crossings with Peak Amplitudes) based on ZCPA feature. The new feature includes the information of speech signals and its difference signal. It can improve system performance to some extent. The recognition network uses HMM. The experiment results show that the results of using CZCPA feature with Bark wavelet filters as front-end processor are superior to the results of using ZCPA feature with FIR filter as front-end in speech recognition system. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/IROS.2006.282434 | IROS |
Keywords | Field | DocType |
FIR filters,filtering theory,speech recognition,wavelet transforms,Bark wavelet,CZCPA Features,FIR filter bank,combining zero crossings with peak amplitudes,frequency band division demand,front-end processor,speech recognition system,Bark scale,Feature extraction,Speech recognition,Wavelet | Pattern recognition,Computer science,Filter bank,Second-generation wavelet transform,Speech recognition,Artificial intelligence,Discrete wavelet transform,Cascade algorithm,Stationary wavelet transform,Wavelet packet decomposition,Wavelet transform,Wavelet | Conference |
Citations | PageRank | References |
1 | 0.36 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xueying Zhang | 1 | 38 | 9.52 |
Jing Bai | 2 | 7 | 1.95 |