Skip to content

Publications

Detail of publication

Citation

Zbyněk Zajíc and Machlica Lukáš and Müller Luděk : Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation . IEEE 11th International Conference on Signal Processing, p. 507-510, Beijing, 2012.

Download PDF

PDF

Abstract

The aim of this work is to propose a refinement of the shift-MLLR (shift Maximum Likelihood Linear Regression) adaptation of an acoustics model in the case of limited amount of adaptation data, which can lead to ill-conditioned transformations matrices. We try to suppress the influence of badly estimated transformation parameters utilizing the bottleneck Artificial Neural Network (ANN). The ill-conditioned shift-MLLR transformation is propagated through a bottleneck ANN (suitably trained beforehand), and the output of the net is used as the new refined transformation. To train the ANN the well and the badly conditioned shift-MLLR transformations are used as outputs and inputs of ANN, respectively.

Detail of publication

Title: Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation
Author: Zbyněk Zajíc ; Machlica Lukáš ; Müller Luděk
Language: English
Year: 2012
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: IEEE 11th International Conference on Signal Processing
Page: 507 - 510
Address: Beijing
/ 2013-02-18 16:34:13 /

Keywords

ASR, Adaptation, shift-MLLR, ANN, bottleneck

BibTeX

@MISC{ZbynekZajic_2012_BottleneckANN,
 author = {Zbyn\v{e}k Zaj\'{i}c and Machlica Luk\'{a}\v{s} and M\"{u}ller Lud\v{e}k},
 title = {Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation},
 year = {2012},
 journal = {IEEE 11th International Conference on Signal Processing},
 address = {Beijing},
 pages = {507-510},
 url = {http://www.kky.zcu.cz/en/publications/ZbynekZajic_2012_BottleneckANN},
}