Name
Abstract | ||
|---|---|---|
Dynamic Time Warping (DTW) is a kind of simple and efficient method in speech identification. The human pronounces with variable pitch period at different time. Speech parameter extraction with fixed-length window will cause error discrimination to some extent because of different signal period in windows. Sliding windows with variable length is to select sliding windows with different length according to the variation of the pitch period of the speech signal in order that each window contains speech signals with identical period.Speech segmentation via sliding windows with variable length can eliminate the errors caused by the difference of speech signals contained in each window. Experimental results verify the improvement on the precision of speech identification. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/HIS.2009.66 | HIS (1) |
Keywords | Field | DocType |
lp cepstral,speech recognition,variable sliding window,identical period,speech segmentation,different signal period,speech signal,speech parameter extraction,variable pitch period,speech identification algorithm,pitch period,cepstral analysis,error discrimination,variable sliding window dtw,speech identification,dynamic time warping,different length,variable length,speech processing,hidden markov models,sliding window,cepstrum,algorithm design and analysis,speech | Speech processing,Algorithm design,Sliding window protocol,Pattern recognition,Dynamic time warping,Segmentation,Computer science,Cepstrum,Speech recognition,Artificial intelligence,Speech segmentation,Hidden Markov model | Conference |
Volume | ISBN | Citations |
1 | 978-0-7695-3745-0 | 3 |
PageRank | References | Authors |
0.49 | 1 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guangyu Kang | 1 | 7 | 1.91 |
| Shize Guo | 2 | 145 | 23.21 |