The authors address issues for improving handsfree speech recognition performance in different car environments using a single distant microphone. In this paper, a nonlinear multiple-regression-based enhancement method for in-car speech recognition is proposed. In order to develop a data-driven in-car recognition system, they develop an effective algorithm for adapting the regression parameters to different driving conditions. They also devise the model compensation scheme by synthesizing the training data using the optimal regression parameters and by selecting the optimal HMM for the test speech. Based on isolated word recognition experiments conducted in 15 real car environments, the proposed adaptive regression approach shows an advantage in average relative word error rate (WER) reductions of 52.5% and 14.8%, compared to original noisy speech and ETSI advanced front end, respectively.
Robust in-car speech recognition based on nonlinear multiple regressions
EURASIP Journal on Advances in Signal Processing (Internet) ; ID 16921/1-ID 16921/10
2007
10 Seiten, 9 Bilder, 2 Tabellen, 37 Quellen
Aufsatz (Zeitschrift)
Englisch
Robust Speech Recognition System for Avionics
Online Contents | 2004
|Testing for robust speech recognition performance
Tema Archiv | 1986
|Recognition Method for Change Point of Traffic Flow Linear Regressions
Tema Archiv | 2012
|Extended VTS for noise-robust speech recognition
TIBKAT | 2009
|Noise Robust Speech Recognition Using Prosodic Information
Springer Verlag | 2005
|