Frontend post-processing and backend model enhancement on the Aurora 2.0/3.0 databases
نویسندگان
چکیده
We investigate a highly effective and extremely simple noiserobust front end based on novel post-processing of standard MFCC features on the Aurora databases. It performs remarkably well on both the Aurora 2.0 and Aurora 3.0 databases without requiring any increase in model complexity. Our experiments on Aurora 2.0 have been reported in [1]. In this paper, we evaluate this technique on the Aurora 3.0 corpus, and present updated results on Aurora 2.0. Results in the past have shown that endpointing (i.e., presegmentation) on Aurora 3.0 can yield significant improvements. Our experiments reported herein show that our approach integrates well with this endpointing, namely we obtain additional significant improvements. Overall, on Aurora 3.0 we obtain a 47.17% improvement over the segmented baseline. Also, our most recent Aurora 2.0 results show an overall improvement of 41.09% over the baseline for the matched training conditions, and 65.07% for the mis-matched conditions.
منابع مشابه
Frontend Post-processing and Backend M Aurora 2.0/3.0 Datab
We investigate a highly effective and extremely simple noiserobust front end based on novel post-processing of standard MFCC features on the Aurora databases. It performs remarkably well on both the Aurora 2.0 and Aurora 3.0 databases without requiring any increase in model complexity. Our experiments on Aurora 2.0 have been reported in [1]. In this paper, we evaluate this technique on the Auro...
متن کاملBlind MVA Speech Feature Processing on Aurora 2.0
This paper is focused on the MVA (mean subtraction, variance normalization, and ARMA filtering) feature postprocessing scheme for noise-robust automatic speech recognition. MVA has shown great success in the past on the Aurora 2.0 and 3.0 corpora. To test its generality, in this work MVA is blindly applied to many different acoustic feature extraction methods, and is evaluated using the Aurora ...
متن کاملNoise-robust speech feature processing with empirical mode decomposition
In this article, a novel technique based on the empirical mode decomposition methodology for processing speech features is proposed and investigated. The empirical mode decomposition generalizes the Fourier analysis. It decomposes a signal as the sum of intrinsic mode functions. In this study, we implement an iterative algorithm to find the intrinsic mode functions for any given signal. We desi...
متن کاملCombining User Interaction, Speculative Query Execution and Sampling in the DICE System
The interactive exploration of data cubes has become a popular application, especially over large datasets. In this paper, we present DICE, a combination of a novel frontend query interface and distributed aggregation backend that enables interactive cube exploration. DICE provides a convenient, practical alternative to the typical offline cube materialization strategy by allowing the user to e...
متن کاملMulti-candidate missing data imputation for robust speech recognition
The application of Missing Data Techniques (MDT) to increase the noise robustness of HMM/GMM-based large vocabulary speech recognizers is hampered by a large computational burden. The likelihood evaluations imply solving many constrained least squares (CLSQ) optimization problems. As an alternative, researchers have proposed frontend MDT or have made oversimplifying independence assumptions for...
متن کامل