This paper presents a novel training method of an eigenvoice Gaussian mixture model (EV-GMM) effectively using non-parallel data sets for many-to-many eigenvoice conversion, which...
Sensitivity analysis is one of the most interesting and preoccupying areas in optimization. Many attempts are made to investigate the problem's behavior when the input data c...
Abstract We demonstrate a SIMD C++ genetic programming system on a single 128 node parallel nVidia GeForce 8800 GTX GPU under RapidMind's GPGPU Linux software by predicting te...
Quantizers for probabilistic sources are usually optimized for mean-squared error. In many applications, maintaining low relative error is a more suitable objective. This measure ...
This paper addresses the problem of acoustic echo cancellation in non-linear environments. The rst contribution relates to the use of a cascaded model which divides the loudspeake...
Moctar Mossi Idrissa, Christelle Yemdji, Nicholas ...