Switching Linear Dynamic Models for Noise Robust In-Car Speech Recognition

Authors:
Björn Schuller;Martin Wöllmer;Tobias Moosmayr;Günther Ruske;Gerhard Rigoll
Affiliations:
Institute for Human-Machine Communication, Technische Universität München, München, Germany 80290;Institute for Human-Machine Communication, Technische Universität München, München, Germany 80290;BMW Group, Forschungs- und Innovationszentrum, Akustik, Komfort und Werterhaltung, München, Germany 80788;Institute for Human-Machine Communication, Technische Universität München, München, Germany 80290;Institute for Human-Machine Communication, Technische Universität München, München, Germany 80290
Venue:
Proceedings of the 30th DAGM symposium on Pattern Recognition
Year:
2008

Citing 4
Cited 0

Cepstral domain segmental feature vector normalization for noise robust speech recognition

Speech Communication - Special issue on robust speech recognition
Expectation Correction for Smoothed Inference in Switching Linear Dynamical Systems

The Journal of Machine Learning Research
On the Necessity and Feasibility of Detecting a Driver's Emotional State While Driving

ACII '07 Proceedings of the 2nd international conference on Affective Computing and Intelligent Interaction
Switching Linear Dynamical Systems for Noise Robust Speech Recognition

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Performance of speech recognition systems strongly degrades in the presence of background noise, like the driving noise in the interior of a car. We compare two different Kalman filtering approaches which attempt to improve noise robustness: Switching Linear Dynamic Models (SLDM) and Autoregressive Switching Linear Dynamical Systems (AR-SLDS). Unlike previous works which are restricted on considering white noise, we evaluate the modeling concepts in a noisy speech recognition task where also colored noise produced through different driving conditions and car types is taken into account. Thereby we demonstrate that speech enhancement based on Kalman filtering prevails over all standard de-noising techniques considered herein, such as Wiener filtering, Histogram Equalization, and Unsupervised Spectral Subtraction.