Frame-Based Acoustic Feature Integration for Speech Understanding

Abstract : With the purpose of improving Spoken Language Un- derstanding (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 inter- polation. 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 like- lihood ratios, a substantial Concept Error Rate (CER) reduction has been observed on the test part of the French MEDIA corpus.
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00424663
Contributor : Loïc Barrault <>
Submitted on : Friday, October 16, 2009 - 4:54:24 PM
Last modification on : Tuesday, July 2, 2019 - 5:38:02 PM
Long-term archiving on : Wednesday, June 16, 2010 - 12:51:01 AM

File

Barrault-ICASSP2008.pdf
Publisher files allowed on an open archive

Identifiers

Collections

Citation

Loïc Barrault, Christophe Servan, Driss Matrouf, Georges Linarès, Renato de Mori. Frame-Based Acoustic Feature Integration for Speech Understanding. IEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008., Mar 2008, Las Vegas, NV,, United States. pp.4997-5000, ⟨10.1109/ICASSP.2008.4518780⟩. ⟨hal-00424663⟩

Share

Metrics

Record views

178

Files downloads

354