Graduate School and Research Center in Digital Sciences

An evolutionary confidence measurement for spoken term detection

Tejedor, Javier; Echeverria, Alejandro; Wang, Dong

CBMI Conference, 9th International Workshop on Content-Based Multimedia Indexing, 13-15 June 2011, Madrid, Spain

    We propose a new discriminative confidence measurement approach based on an evolution strategy for spoken term detection (STD). Our evolutionary algorithm, named evolutionary discriminant analysis (EDA), optimizes classification errors directly, which is a salient advantage compared with some conventional discriminative models which optimize objective functions based on certain class encoding, e.g. MLPs and SVMs. In addition, with the intrinsic randomness of the evolution strategy, EDA largely reduces the risk of converging to local minimums in model training. This is particularly valuable when the decision boundary is complex, which is the case when dealing with out-of-vocabulary (OOV) terms in STD. Experimental results on the meeting domain in English demonstrate considerable performance improvement with the EDA-based confidence for OOV terms compared with MLPs- and SVMs-based confidences; for in-vocabulary terms, however, no significant difference is observed with the three models. This confirms our conjecture that EDA exhibits more advantage for tasks with complex decision boundaries.

Document Doi Bibtex

Title:An evolutionary confidence measurement for spoken term detection
Type:Conference
Language:English
City:Madrid
Country:SPAIN
Date:
Department:Digital Security
Eurecom ref:3382
Copyright: © 2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+3382, doi = {http://dx.doi.org/10.1109/CBMI.2011.5972537 }, year = {2011}, title = {{A}n evolutionary confidence measurement for spoken term detection}, author = {{T}ejedor, {J}avier and {E}cheverria, {A}lejandro and {W}ang, {D}ong }, booktitle = {{CBMI} {C}onference, 9th {I}nternational {W}orkshop on {C}ontent-{B}ased {M}ultimedia {I}ndexing, 13-15 {J}une 2011, {M}adrid, {S}pain }, address = {{M}adrid, {SPAIN}}, month = {06}, url = {http://www.eurecom.fr/publication/3382} }