A method for determining a dead space to the representation of a plurality of training speakers

摘要

A process is described for determining a dead space to the representation of a plurality of training speakers, in which initially speaker-dependent model - sets for the individual training with the use of training speech data of the individual training be formed, whereby the models (sd) of a model - sets in each case by a plurality of model parameters will be described. For each speaker is then a combined model in many-dimensional vector space by chaining a of the model parameters of the models of the individual training set in each case to form a coherent. Subsequently, a transformation with a reduction in the dimension of the model space base vectors of space - (e φ e φ) is carried out, which a on the variability of the vectors to be transformed based reduction criterion makes use of. In this case, the many-dimensional model space in a first step by means of a base change to a speaker - subspace reduced, in which all are eigen. In a second step, then, in this speaker - n dimensional subspace on which the eigen vectors representing the transformation for the production of the properties of the space - base vectors (e φ e φ) is carried out.