An application constrained front end for speaker verification

Even if the speaker recognition field is very dynamic, few studies concern the constraints linked to the use of a speaker recognition system inside a professional telecommunication network. This paper deals with this problem and proposes some adaptation of such system in the focus of a real world network monitoring application. This work is specifically dedicated to the front-end. Both real-time constraints and distributed architectures are investigated. The signal acquisition takes place on a mobile terminal, while the speaker verification process is performed on a remote server. We propose a frame-by-frame on-line processing for feature extraction, frame selection and normalization. The links between the network speech coder and the speaker recognition system are also investigated, for both the ETSI TETRA speech codec (at 4600 bit/sec) and the NATO STANAG 4591 (at 2400 bit/sec). The proposed solutions are compared with a classical unconstrained front-end (off-line processing).