Title :
Enabling improved speaker recognition by voice quality estimation
Author :
Bartos, Anthony L. ; Nelson, Douglas J.
Author_Institution :
Assurance Technol. Corp., Chantilly, VA, USA
Abstract :
Presented is a method to mitigate noise and interference in automated speaker identification (SID). This process uses the MIT/LL SID module without modifications. In this process, speaker models are built for a lattice of signal to noise ratio (SNR) levels. The SNR of the received signal is estimated by first applying speech activity detection to identify portions of the signal that actually contain speech. A voice quality estimation process is then applied to estimate the SNR of the received signal. The speaker models representing the SNR of the received signal are dynamically loaded, and conventional SID is applied. In training, the SNR of each training signal is estimated, and the signal is modified by adding noise to create a signal at the desired SNR. Using this process, each signal may be used to train models at any SNR level less than or equal to the SNR of the original signal. The process has been fully implemented and is completely automated.
Keywords :
interference suppression; signal denoising; signal detection; speaker recognition; MIT/LL SID module; SNR level; automated speaker identification; improved speaker recognition; interference mitigation; noise mitigation; received signal SNR; signal to noise ratio; speaker models; speech activity detection; voice quality estimation process; Load modeling; Signal to noise ratio; Speech; Speech processing; Training; Training data; EER; Equal Error Rate; LID; Language ID; SAD; SID; SNR; Signal to Noise Ratio; Speaker ID; Speech Activity Detection; VAD; VQE; Voice Quality Estimate; voice Activity Detection;
Conference_Titel :
Signals, Systems and Computers (ASILOMAR), 2011 Conference Record of the Forty Fifth Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
978-1-4673-0321-7
DOI :
10.1109/ACSSC.2011.6190071
