|
|
|
| Investigation of Improved Approaches to Bayes Risk Decoding |
| XU Hai-hua (徐海华), ZHU Jie (朱 杰) |
(Department of Electronic Engineering, Shanghai Jiaotong University,
Shanghai 200240, China) |
|
|
|
|
Abstract Abstract: Bayes risk (BR) decoding methods have been widely
investigated in the speech recognition area due to its flexibility and
complexity compared with the maximum a posteriori (MAP) method regarding to
minimum word error (MWE) optimization. This paper investigates two improved
approaches to the BR decoding, aiming at minimizing word error. The novelty
of the proposed methods is shown in the explicit optimization of the
objective function, the value of which is calculated by an improved forward
algorithm on the lattice. However, the result of the first method is
obtained by an expectation maximization (EM) like iteration, while the
result of the second one is achieved by traversing the confusion network
(CN), both of which lead to an optimized objective function value with
distinct approaches. Experimental results indicate that the proposed methods
result in an error reduction for lattice rescoring, compared with the
traditional CN method for lattice rescoring.
|
|
Received: 11 July 2010
Published: 29 October 2011
|
|
|
|
Corresponding Authors:
XU Hai-hua (徐海华)
E-mail: haihua.xu@aispeech.com
|
|
|
|
|
|
|
