Giorgio Biagetti, Alessandro Curzi, Massimo Mercuri, and Claudio Turchetti
MLLR, CMLLR, ICMLLR, DSR, SI, SD
In this paper an effective technique for speaker adaptation on the feature domain is presented. This technique starts from the well known maximum-likelihood linear regression (MLLR) auxiliary function to obtain the constrained MLLR transformation in an iterative fashion. The proposed approach is particularly suitable to be implemented on the client side of a distributed speech recognition scheme, due to the reduced number of iterations required to reach convergence. Extensive experimentation using the CMU Sphinx~4 ASR system along with a preliminarily trained speaker-independent acoustic model for the Italian language, in a setting designed for large-vocabulary continuous speech recognition, demonstrates the effectiveness of the approach even with small amounts of adaptation data.
Important Links:
Go Back
