Abstract | ||
---|---|---|
This paper presents a new approach to extract antinoisy speech feature: weighting combination zerocrossings with peak amplitudes, which is based on auditory model. It is an improved model of zerocrossings with peak amplitudes. This approach uses the speech signal and its difference signal as input. The frequency information of speech signal is obtained by upward-going zero-crossing intervals, and the intension information is incorporated by compressing nonlinearly amplitudes. The speech feature is weighted according to the auditory characteristics by using weighting function, and then the output feature is obtained. The recognition part uses HMM. Experimental results demonstrate that this new feature is more robust than the old feature in noise environment. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ICICIC.2006.398 | ICICIC (3) |
Keywords | Field | DocType |
antinoisy speech feature,weighting combination zcpa,peak amplitude,auditory characteristic,speech signal,old feature,speech feature,output feature,auditory model,robust speech recognition,new feature,difference signal,hidden markov models,weight function,speech recognition,zero crossing,feature extraction,hmm | Weighting,Zero crossing,Pattern recognition,Computer science,Intension,Feature extraction,Speech recognition,Artificial intelligence,Hidden Markov model | Conference |
ISBN | Citations | PageRank |
0-7695-2616-0 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xueying Zhang | 1 | 2 | 2.08 |
Wuzhou Liang | 2 | 0 | 0.34 |