Search

When speaker is recorded from distance, a microphone captures speech signal corrupted by room reverberation and environmental noise. In this paper, we aim to reduce the effect of detrimental late reverberation and noise on speaker recognition based on x-vector extractor. We investigate features that are robust against room reverberation and dedicated Probabilistic Linear Discriminant Analysis (PLDA) training. The results of performed experiments indicate that an improvement in the performance of a speaker embeddings system is mostly brought about by careful PLDA training with data adjusted to the test conditions. An improvement in reverberant conditions is also observed for the reverberation robust features, such as Mel-frequency Cepstral Coefficients (MFCC) from the dereverberated signal and Mean Hilbert Envelope Coefficients (MHEC). This work has been performed as part of our contribution to the Voices Obscured in Complex Environmental Settings (VOiCES) from a Distance Challenge 2019, in which the reported methods led to a 12% and 32% relative gains in terms of the Equal Error Rate for the VOiCES development and evaluation datasets, respectively.

The aim of our work is to develop the software for caller identification or to create his characteristic by analysis of his voice. Based on collected speech samples, our system aims to identify emergency callers both on-line and off-line. This homeland security project covers speaker recognition (when speaker's speech sample is known), speaker's gender, age detection and recognition of emotions. Proposed system is not limited to bio-metrics. The goal of this application is to provide an innovative, supporting tool for rapid and accurate threat detection and threat neutralization. This complex system will include: a speech signal analysis, an automatic development of speech patterns database and appropriate classification methods.

The transmission and analysis of video is frequently used for a variety of applications outside the entertainment sector, and it is generally used to perform specific tasks. The Quality of Experience (QoE) concept for video content used for entertainment differs significantly from the QoE of video used for recognition tasks, because in the latter case the subjective satisfaction of the user depends on achieving the given task, e.g. event detection or object recognition. Additionally, the quality of video used by a human observer is distinct from objective video quality used in computer processing — Computer Vision. The VQiPS (Video Quality in Public Safety) Working Group, established in 2009 and supported by the U.S. Department of Homeland Security's Office for Interoperability and Compatibility, has been developing a user guide for public safety video applications. According to VQiPS, the ability to achieve a recognition task is influenced by many parameters, and five of them have been selected as being of particular importance. They are: usage time-frame, discrimination level, target size, lighting level, and level of motion. These parameters form what are referred to as Generalized Use Classes, or GUCs. The aim of our research was to develop algorithms that would automatically support classification of input sequences into one of the GUCs. Target size and lighting level parameters were approached. The described experiment reveals the ambiguity and hesitation of the experts during the manual target size determination process. However, the developed automatic methods of target size classification make it possible to determine GUC parameters with satisfactory efficiency at compliance levels of 70% with end-users opinion. Lighting levels of the entire sequence can be classified with an efficiency reaching 93%.