The lack of labeled background data makes a big performance gap between cosine and Probabilistic Linear Discriminant Analysis (PLDA) scoring baseline techniques for i-vectors in speaker recognition. Although there are some ...

This thesis concerns the detection of overlapping speech segments and its further application for the improvement of speaker diarization performance. We propose the use of three spatial cross-correlation-based parameters ...

Speech dynamic features, which provide smoothed estimates of the derivatives of the spectral parameter trajectories in the current frame, are routinely used in current speech recognition systems in combination with short-term ...

Most state-of-the-art Deep Learning systems for text-independent speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a ...

We study the touchscreen data as behavioral biometrics. The goal was to create an end-to-end system that can transparently identify users using raw data from mobile devices. The touchscreen biometrics was researched only ...

A correct choice of voice signal modeling method is essential to obtain good results in automatic speech recogniton. In this paper, a comparative study betwen two speech signal models, Linear Prediction Coeficients and ...

In speech recognition, a discriminative frequency weighting can be achieved by decorrelating the frequency sequence of log mel-scaled filter-bank energies with a computationally inexpensive filter. We show how the spectral ...

This work presents a novel two-step algorithm to estimate the orientation of speakers in a smart-room environment equipped with microphone arrays. First the position of the speaker is estimated by the SRP-PHAT algorithm, ...

In this paper we propose an impostor selection method for a Deep Belief Network (DBN) based system which models i-vectors in a multi-session speaker verification task. In the proposed method, instead of choosing a ...