Human speech often has events that we will call trivial events, e.g., cough, laugh and sniff. Compared to regular speech, these trivial events are usually short and variable, thus generally regarded as not speaker discriminative and so are largely ignored by present speaker recognition research. However, these trivial events are highly valuable in some particular circumstances such as forensic examination, as they are less subjected to intentional change, so can be used to discover the genuine speaker from disguised speech.In this paper, we collect a trivial event speech database that involves 75 speakers and 6 types of events, and report preliminary speaker recognition results on this database, by both human listeners and machines. Particularly, the deep feature learning technique recently proposed by our group is utilized to analyze and recognize the trivial events, leading to acceptable equal error rates (EERs) ranging from 5% to 15% despite the extremely short durations (0.2-0.5 seconds) of these events. Comparing different types of events, 'hmm' seems more speaker discriminative.

No abstract

No abstract

No abstract

This paper proposes an improved XGBoost Wi-Fi indoor positioning algorithm aiming at the accuracy problem caused by the change of environment.The method first uses Extreme Gradient Boosting (XGBoost) algorithm to establish indoor positioning model, which can achieve indoor positioning. When the environment changes, further combine error compensation (EC) method to improve the initial positioning. In addition, the positioning trajectory is compared with the actual trajectory and the unimproved positioning trajectory to verify the stability of the algorithm. The experimental results show that the 80-th percentile of the achieved accuracy is 1.11m after the change of environment, which is significantly better than the unimproved positioning algorithms based on support vector machine, random forest and extreme gradient promotion, and the obtained positioning trajectory tends to converge with the actual trajectory.