Loading...
Please wait, while we are loading the content...
Similar Documents
Bispectrum Mel-frequency Cepstrum Coefficients for Robust Speaker Identification
| Content Provider | CiteSeerX |
|---|---|
| Author | Akgül, Tayfun Özkurt, Tolga Esat Ülüğ, Ufuk |
| Abstract | In this paper, we introduce the use of bispectrum slice for mel-frequency cepstrum coefficients as robust text-independent speaker identification. The main advantage of using the bispectrum is to be able to suppress additive Gaussian noise while preserving the phase information of the signal. In order to obtain cepstral coefficients, features of the speech signal are extracted by mel-frequency filter banks, the cosine transform and the logarithm operator. Under various noisy test utterances, we compare and present the performances of the methods which use the bispectrum and the classical mel-frequency cepstrum coefficients. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Phase Information Mel-frequency Filter Bank Bispectrum Slice Additive Gaussian Noise Main Advantage Robust Text-independent Speaker Identification Classical Mel-frequency Cepstrum Coefficient Various Noisy Test Utterance Bispectrum Mel-frequency Cepstrum Coefficient Logarithm Operator Cosine Transform Mel-frequency Cepstrum Coefficient Speech Signal Cepstral Coefficient Robust Speaker Identification |
| Content Type | Text |
