Bayesian subspace methods for acoustic signature recognition of vehicles

Vehicles may be recognized from the sound they make when moving, i.e., from their acoustic signature. Characteristic patterns may be extracted from the Fourier description of the signature and used for recognition. This paper compares conventional methods used for speaker recognition, namely, systems based on Mel-frequency cepstral coefficients (MFCC) and either Gaussian mixture models (GMM) or hidden Markov models (HMM), with Bayesian subspace method based on the short term Fourier transform (STFT) of the vehicles' acoustic signature. A probabilistic subspace classifier achieves a 11.7% error for the ACIDS database, outperforming conventional MFCC-GMM- and MFCC-HMM-based systems by 50%.