Digital Speech Watermarking for Authenticity of Speaker in Speaker Recognition System

2016 International Conference on Micro-Electronics and Telecommunication Engineering (ICMETE) ◽

10.1109/icmete.2016.13 ◽

2016 ◽

Cited By ~ 2

Author(s):

Nihalkumar Desai ◽

Nikunj Tahilramani

Keyword(s):

Speaker Recognition ◽

Recognition System ◽

Speech Watermarking ◽

Digital Speech Watermarking

Download Full-text

Semi-fragile digital speech watermarking for online speaker recognition

EURASIP Journal on Audio Speech and Music Processing ◽

10.1186/s13636-015-0074-5 ◽

2015 ◽

Vol 2015 (1) ◽

Cited By ~ 10

Author(s):

Mohammad Ali Nematollahi ◽

Mohammad Ali Akhaee ◽

S. A. R. Al-Haddad ◽

Hamurabi Gamboa-Rosales

Keyword(s):

Speaker Recognition ◽

Speech Watermarking ◽

Digital Speech Watermarking

Download Full-text

Robust Digital Speech Watermarking For Online Speaker Recognition

Mathematical Problems in Engineering ◽

10.1155/2015/372398 ◽

2015 ◽

Vol 2015 ◽

pp. 1-12 ◽

Cited By ~ 8

Author(s):

Mohammad Ali Nematollahi ◽

Hamurabi Gamboa-Rosales ◽

Mohammad Ali Akhaee ◽

S. A. R. Al-Haddad

Keyword(s):

Speaker Recognition ◽

Speaker Verification ◽

Discrete Wavelet ◽

Specific Information ◽

Massachusetts Institute ◽

Massachusetts Institute Of Technology ◽

Discrete Wavelet Packet Transform ◽

Speech Watermarking ◽

Digital Speech Watermarking ◽

Institute Of Technology

A robust and blind digital speech watermarking technique has been proposed for online speaker recognition systems based on Discrete Wavelet Packet Transform (DWPT) and multiplication to embed the watermark in the amplitudes of the wavelet’s subbands. In order to minimize the degradation effect of the watermark, these subbands are selected where less speaker-specific information was available (500 Hz–3500 Hz and 6000 Hz–7000 Hz). Experimental results on Texas Instruments Massachusetts Institute of Technology (TIMIT), Massachusetts Institute of Technology (MIT), and Mobile Biometry (MOBIO) show that the degradation for speaker verification and identification is 1.16% and 2.52%, respectively. Furthermore, the proposed watermark technique can provide enough robustness against different signal processing attacks.

Download Full-text