Academic Commons

Articles

Speech Feature Smoothing for Robust ASR

Chen, Chia-Ping; Bilmes, Jeff; Ellis, Daniel P. W.

In this paper, we evaluate smoothing within the context of the MVA (mean subtraction, variance normalization, and ARMA filtering) post-processing scheme for noise-robust automatic speech recognition. MVA has shown great success in the past on the Aurora 2.0 and 3.0 corpora even though it is computationally inexpensive. Herein, MVA is applied to many acoustic feature extraction methods, and is evaluated using Aurora 2.0. We evaluate MVA post-processing on MFCCs, LPCs, PLPs, RASTA, Tandem, Modulation-filtered Spectrogram, and Modulation Cross- CorreloGram features. We conclude that while effectiveness does depend on the extraction method, the majority of features benefit significantly from MVA, and the smoothing ARMA filter is an important component. It appears that the effectiveness of normalization and smoothing depends on the domain in which it is applied, being most fruitfully applied just before being scored by a probabilistic model. Moreover, since it is both effective and simple, our ARMA filter should be considered a candidate method in most noise-robust speech recognition tasks.

Files

Also Published In

Title
2005 IEEE International Conference on Acoustics, Speech, and Signal Processing: Proceedings: March 18-23, 2005, Pennsylvania Convention Center/Marriott Hotel, Philadelphia, Pennsylvania, USA
DOI
https://doi.org/10.1109/ICASSP.2005.1415166

More About This Work

Academic Units
Electrical Engineering
Publisher
IEEE
Published Here
June 28, 2012
Academic Commons provides global access to research and scholarship produced at Columbia University, Barnard College, Teachers College, Union Theological Seminary and Jewish Theological Seminary. Academic Commons is managed by the Columbia University Libraries.