Download now Free registration required
In this paper, speech signal having information up to 4 kHz is termed as NarrowBand (NB) speech and the other having information up to 8 kHz is termed as WideBand (WB) speech. The objective is to demonstrate the significance of speaker information present in the WB speech. A Speaker Verification (SV) system is developed using the Mel-Frequency Cepstral Coefficients (MFCCs) computed from the WB speech and modeled using Gaussian Mixture Models (GMM). For comparison, a SV system is also developed from the corresponding NB speech. The experimental results show that the SV performance improves for WB speech and the improvement is significant under degraded conditions.
- Format: PDF
- Size: 155.58 KB