EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology
2nd INTERSPEECH Event

Aalborg, Denmark
September 3-7, 2001

                 

A Novel Target-Driven MLLR Adaptation Algorithm with Multi-Layer Structure

Jia Lei, Xu Bo

Institute of Automation, Chinese Academy of Science, China

This paper presents a novel target-driven MLLR adaptation algorithm with multiply layer structure, which is based on the thorough analysis of MLLR using the generation of regression class trees. The new algorithm is constructed on the target-driven principal. It generates the regression class dynamically, basing on the outcome of the former MLLR transformation. The regression classes is defined in order to have the maximizing increase of the auxiliary function, which is in proportional to the likelihood of the occurrence of the adaptation data. Because of the new algorithm's special transformation structure, computation load in performing transformation is much reduced. In comparison with the conventional MLLR using the generation of regression class trees, the new algorithm give a further error reduction 10% and has only half computation time consuming.

Full Paper

Bibliographic reference.  Lei, Jia / Bo, Xu (2001): "A novel target-driven MLLR adaptation algorithm with multi-layer structure", In EUROSPEECH-2001, 1225-1228.