In this paper we propose to employ directional statistics in a complex vector space to approach the problem of blind speech separation in the presence of spatially correlated noise. We interpret the values of the short time Fourier transform of the microphone signals to be draws from a mixture of complex Watson distributions, a probabilistic model which naturally accounts for spatial aliasing. ...

In studies of the cocktail party problem, the number and locations of maskers are typically fixed throughout a block of trials, which leaves out uncertainty that exists in real-world environments. The current experiments examined whether there is (1) improved speech intelligibility and (2) increased spatial release from masking (SRM), as predictability of the number/locations of speech maskers ...

anti-lock braking system (abs) is a nonlinear and time varying system including uncertainty, so it cannot be controlled by classic methods. intelligent methods such as fuzzy controller are used in this area extensively; however traditional fuzzy controller using simple type-1 fuzzy sets may not be robust enough to overcome uncertainties. for this reason an interval type-2 fuzzy controller is de...

Speech enhancement aims to improve speech quality by using various algorithms. It may sound simple, but what is meant by the word quality. It can be at least clarity and intelligibility, pleasantness, or compatibility with some other method in speech processing. Wiener filter are rather simple and workable, but after the estimation of the background noise, one neglects the fact that the signal ...

In this paper, we introduce Bayesian networks architecture for combining speech-based information with that from another modality for error handling in human-robot dialogue system. In particular, we report on experiments interpreting speech and laser scanner signals in the dialogue management system of the autonomous tour-guide robot RoboX, successfully deployed at the Swiss National Exhibition...

Introduction: Frequency domain speech enhancement is focused mainly on improved estimation of spectral attenuation factors with the assumption of given noise statistics. However, in practice, the noise statistics exhibit fluctuations from frame to frame. Thus, a method for robust estimation of the noise statistics is investigated in this Letter. Conventional noise estimation can be classified i...

We consider the problem of acoustic modeling of noisy speech data, where the uncertainty over the data is given by a Gaussian distribution. While this uncertainty has been exploited at the decoding stage via uncertainty decoding, its usage at the training stage remains limited to static model adaptation. We introduce a new Expectation Maximisation (EM) based technique, which we call uncertainty...

this paper deals with a globally convergent adaptive and sliding mode control of a cart-pole inverted pendulum for trajectory tracking in the presence of a bounded measurement noise and parameter uncertainty. two kinds of controllers have been used for evaluation of tracking error in presence of a bounded noise; as a result, we want to compare that at what time we can see the convergence of tra...