150 likes | 293 Views
GSTC UGR. HIWIRE MEETING Paris, February 11, 2005. JOSÉ C. SEGURA LUNA. Schedule. AURORA 4 HTK-based setup Baseline results (AURORA databases) MFCC with C0 and CMN AFE Additional results CMVN HEQ Work in progress WP1: Improved HEQ WP2: User independence & robustness.
E N D
GSTC UGR HIWIRE MEETINGParis, February 11, 2005 JOSÉ C. SEGURA LUNA
Schedule • AURORA 4 HTK-based setup • Baseline results (AURORA databases) • MFCC with C0 and CMN • AFE • Additional results • CMVN • HEQ • Work in progress • WP1: Improved HEQ • WP2: User independence & robustness
AURORA 4 HTK-based setup • ETSI AURORA 4 evaluation • Baseline system based on ISIP speech recognition system • Main drawbacks: • CPU time for experiments (specially for decoding) • Scripts are excessively complex to use • Described in: • N. Parihar and J. Picone, "DSR Front End LVCSR Evaluation - AU/384/02," Aurora Working Group, ETSI, December 06, 2002. • G. Hirsch, "Experimental Framework for the Performance Evaluation of Speech Recognition Front-ends on a Large Vocabulary Task, Version 2.0," ETSI STQ-Aurora DSR Working Group, November 19, 2002.
AURORA 4 HTK-based setup • HTK-based setup for AURORA 4 evaluations • Features • 12MFCC + C0 (CMS) + Δ + Δ Δ • Cross-word tree-based tied-state tri-phones • 3 states / 6 Gaussians per state • Back-off bi-gram language model • Same as used in ISIP setup • Pruning is performed as in ISIP setup • Available for partners at: http://www.hiwire.org
AURORA 4 HTK-based setup • Performance comparisons (HTK-based setup vs. ISIP) • Training clean models from scratch takes 3h52‘ on a 2.66GHz 12 MFCCs + C0 (CMS) + +
Baseline results • HIWIRE baseline results: 12 MFCCs + C0 (CMS) + + AURORA 2
Baseline results • AFE AURORA 2
Baseline results • AURORA 3 word error rates
Work in progress (WP1) • Improved equalization • Modeling Speech & Noise separately • First results with Gaussian models • Very promising on AURORA 4 • Need to be evaluated on AURORA 2 & 3 • Next • Use more detailed / nonparametric models • Incorporate dynamic features
Work in progress (WP1) • VAD & Noise reduction • Baseline evaluations • AURORA 2 & 3 already done • AURORA 4 to be ready on June • Integration with parametric techniques • Speech & Noise equalization
Work in progress (WP2) • HEQ-based user robustness • Ready for AURORA 4 • Working in WSJ1 baseline • HEQ-based user adaptation • MLLR baseline • Estimation of MLLR transformations using HEQ • Working in WSJ1 baseline
GSTC UGR HIWIRE MEETINGParis, February 11, 2005 JOSÉ C. SEGURA LUNA