Rescoring of N-Best Hypotheses Using Top-Down Selective Attention for Automatic Speech Recognition

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 250
  • Download : 0
In this letter, we propose an N-best rescoring system that integrates attentional information for locally confusing words extracted from alternative hypotheses to a conventional speech recognition system. The attentional information is derived by adapting a test input feature for the word of interest, which is motivated by the top-down selective attention mechanism of the brain. To rescore the competing hypotheses, we define a new confidence measure that contains both the conventional posterior probability and the attentional information for the confusing words. In addition, a neural network is designed to provide different weights within the confidence measure for each utterance. The network is then optimized to minimize the word error rates. Tests on the Wall Street Journal and Aurora4 speech recognition tasks were conducted, and our best results achieve a word error rate of 3.83% and 11.09%, yielding a relative reduction of 5.20% and 2.55% over baselines, respectively.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2018-02
Language
English
Article Type
Article
Keywords

DEEP NEURAL-NETWORKS; BRAIN; MODEL

Citation

IEEE SIGNAL PROCESSING LETTERS, v.25, no.2, pp.199 - 203

ISSN
1070-9908
DOI
10.1109/LSP.2017.2772828
URI
http://hdl.handle.net/10203/239445
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0