Sciweavers

ICASSP
2008
IEEE

Frame-based acoustic feature integration for speech understanding

13 years 9 months ago
Frame-based acoustic feature integration for speech understanding
With the purpose of improving Spoken Language Understanding (SLU) performance, a combination of different acoustic speech recognition (ASR) systems is proposed. State a-posteriori probabilities obtained with systems using different acoustic feature sets are combined with log-linear interpolation. In order to perform a coherent combination of these probabilities, acoustic models must have the same topology (i.e. same set of states). For this purpose, a fast and efficient twin model training protocol is proposed. By a wise choice of acoustic feature sets and log-linear interpolation of their likelihood ratios, a substantial Concept Error Rate (CER) reduction has been observed on the test part of the French MEDIA corpus.
Loic Barrault, Christophe Servan, Driss Matrouf, G
Added 30 May 2010
Updated 30 May 2010
Type Conference
Year 2008
Where ICASSP
Authors Loic Barrault, Christophe Servan, Driss Matrouf, Georges Linares, Renato de Mori
Comments (0)