Afhalen na 1 uur in een winkel met voorraad
Gratis thuislevering in België vanaf € 30
Ruim aanbod met 7 miljoen producten

Afhalen na 1 uur in een winkel met voorraad
Gratis thuislevering in België vanaf € 30
Ruim aanbod met 7 miljoen producten

Winkels

Verlanglijstje

Winkels

Verlanglijstje

Zoeken

Volg ons op

140 winkels

Wist je dat er in Vlaanderen voor iedereen een Standaard Boekhandel is binnen een straal van 7 km?

Vind hier een winkel

€ 105,95

+ 211 punten

Levering 2 à 3 weken

Eenvoudig bestellen

Veilig betalen

Gratis thuislevering vanaf € 30 (via bpost)

Gratis levering in je Standaard Boekhandel

Omschrijving

In recent years, while speaker recognition holds considerable promise, its widespread adoption has been hindered by suboptimal performance marked by its low accuracy and reliability issues. However, addressing these challenges is essential to fully exploit the capabilities of voice biometric recognition with surveys indicating preference for voice biometrics. In situations where remote speaker biometric authentication is employed, maintaining the integrity of extracted cepstral feature vectors becomes paramount in presence of channel noise. To enhance the accuracy of speaker recognition in remote applications, a novel approach is proposed where Low-Density Parity-Check (LDPC) codes and Polar codes are used for both storage and transmission of extracted Mel-frequency cepstral coefficients (MFCC) derived from voice samples. Four proposed and implemented methods are described which result in the lower bit error rates over noisy channels as well as high accuracy rate for remote speaker recognition system. This book concludes with the suggestive use of LDPC and Polar coding as an integral part of remote speaker recognition as a part of multimodal biometric authentication system.