No abstract

This paper presents convergence characteristics of stereophonic echo cancellers with pre-processing. The convergence analysis of the averaged tap-weights show that the convergence characteristics depends on the relation between the impulse response in the far-end room and the changes of the pre-processing filters. Examining the uniqueness of the solution in the frequency domain leads us to the same relation. Computer simulation results show the validity of these analyses.

A learning algorithm is proposed for fully recurrent convolutive blind source separation. Let s i (n) and x j (n) be the signal sources and the observations. z). In many practical applications, this assumption is acceptable. Based on this assumption,

This paper proposes a stereophonic acoustic echo canceller with randomly time-varying second-order pre-processing filters. A quantitative approach for the convergence speed assessment by using time-averaged correlation matrix is also introduced. Simulation results show that the convergence speed of the proposed algorithm is more than twice as fast as that of a conventional pre-processor. The quantitative approach provides us with a good overview for the convergence speed assessments.

In this paper, a recurrent iieural network(RNN) is applied to approximating one to N many valued mappings. The RNN described in this paper has a feedback loop from an output to an input in addition to t h e conventional multi layer neural network(MLNN). The feedback loop causes dynamic output properties. T h e convergence property in these properties can be used for this. approximating problem.In order to avoid conflict by the overlapped target d a t a y*s to the same input I*, the input d a t a set (n, y*) and t h e target d a t a y* are presented to t h e network in learning phase. By this learning, the network function j(x, z ) which satisfies y* = j ( m , y") is formed. In recalling phase, t h e solutions y of y = f ( z , y ) a r e detected by t h e feedback dynamics of RNN. The different solutions for t h e same input x can be gained by changing the initial output value of y.It have been presented in our previous paper that t h e RNN can approximate many valued continuous mappings by introducing the differential condition to learning. However, if t h e mapping has discontinuity or changes of value number, it sometimes shows undesirable behavior. In this paper, the integral condition is proposed in order t o prevent spurious convergence and to spread t h e attractive regions to the approximating points.