Loading...
Please wait, while we are loading the content...
Similar Documents
Review: GMM based Speaker Verification using MFCC Feature Multitaper MFCC for Robust Speaker Verification
| Content Provider | Semantic Scholar |
|---|---|
| Author | Shintri, Rupali G. Bhatia, Sanjiv K. |
| Copyright Year | 2014 |
| Abstract | In speech & audio applications, short-term signal spectrum is often represented using mel-frequency cepstral coefficient (MFCC) computed from a windowed discrete Fourier transform (DFT). Windowing reduces spectral leakage but variance of the spectrum estimate remains high. An extension to windowed DFT is called multitaper method which uses multiple time domain windows (Tapers) with frequency domain averaging. Then detailed statistical analysis of MFCC bias & variance is done. For speaker verification the extracted feature is used to build a model using classifier (GMM), which implements likelihood ratio test to decide whether to accept or reject the speaker. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.ijecce.org/Download/conference/Tech_Pune_2014/69.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
