Abstract
In this paper, we propose an algorithm to discriminate speech from vehicle body impact noise in a car. Depending on road conditions such as the presence of large bumps or unpaved stretches, impact noises from the car body may interfere with the detection of voice commands for a speech-enabled service in the car, which results in degraded service performance. The proposed algorithm classifies each analysis frame of the input signal recorded by a microphone into four different categories such as speech, impact noise, background noise, and mixed speech and impact noise. The classification is based on the likelihood ratio test (LRT) using statistical models constructed by combining signals obtained from the microphone with those from an accelerometer. In other words, the different characteristics detected by both acoustical and mechanical sensing enable better discrimination of voice commands from noise emanating from the vehicle body. The performance of the proposed algorithm is evaluated using a corpus of speech recordings in a car moving at an average velocity of 30-50 km/h with impact noise at various signal-to-noise ratios (SNRs) from -3 to 1 dB, where the SNR is defined as the ratio of the power of speech signals to that of impact noise. It is shown from the experiments that the proposed algorithm achieves a discrimination accuracy of 85%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Wu, K.G., Chen, P.C.: Efficient speech enhancement using spectral subtraction for car hands-free applications. In: roceedings of International Conference on Consumer Electronics (ICCE), Las Vegas, NV, pp. 220–221 (2007)
Ahn, S., Ko, H.: Background noise reduction via dual-channel scheme for speech recognition in vehicular environment. IEEE Transactions on Consumer Electronics 51(1), 22–27 (2005)
Kim, S.M., Kim, H.K.: Hybrid probabilistic adaptation model controller for generalized sidelobe canceller-based target-directional speech enhancement. In: Proceedings of ICASSP, Prague, Czech Republic, pp. 2532–2535 (2011)
Lee, S.-K., Kim, H.-W., Na, E.-W.: Improvement of impact noise in a passenger car utilizing sound metric based on wavelet transform. Journal of Sound and Vibration 329(17), 3606–3619 (2010)
Lee, S.-K., Chae, H.-C.: The application of artificial neural networks to the characterization of interior noise booming in passenger cars. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 218(1), 33–42 (2004)
Wang, Y.S., Lee, C.-M., Kim, D.-G., Xu, Y.: Sound-quality prediction for nonstationary vehicle interior noise based on wavelet pre-processing neural network model. Journal of Sound and Vibration 299(4-5), 933–947 (2007)
Hu, J.S., Cheng, C.C., Liu, W.H., Yang, C.H.: A robust adaptive speech enhancement system for vehicular applications. IEEE Transactions on Consumer Electronics 52(3), 1069–1077 (2006)
Kim, S.M., Kim, H.K.: Probabilistic spectral gain modification applied to beamformer-based noise reduction in a car environment. IEEE Transactions on Consumer Electronics 57(2), 866–872 (2011)
Park, J.H., Kim, S.M., Yoon, J.S., Kim, H.K., Lee, S.J., Lee, Y.K.: SNR–based mask compensation for computational auditory scene analysis applied to speech recognition in a car environment. In: Proceedings of Interspeech, Makuhari, Japan, pp. 725–728 (2010)
Park, J.H., Shin, M.H., Kim, H.K.: Statistical model-based voice activity detection using spatial cues and log energy for dual-channel noisy speech recognition. CCIS, vol. 120, pp. 172–179 (2010)
Sohn, J., Kim, N.S., Sung, W.: A statistical model-based voice activity detection. IEEE Signal Processing Letters 6(1), 1–3 (1999)
Lee, S.Y., Shin, J.W., Yun, H.S., Kim, N.S.: A statistical model based post-filtering algorithm for residual echo suppression. In: Proceedings of Interspeech, Antwerp, Belgium, pp. 858–861 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kim, S.M., Kim, H.K., Lee, S.J., Lee, Y.K. (2011). Discrimination of Speech Activity and Impact Noise Using an Accelerometer and a Microphone in a Car Environment. In: Kim, Th., et al. Communication and Networking. FGCN 2011. Communications in Computer and Information Science, vol 266. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27201-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-27201-1_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27200-4
Online ISBN: 978-3-642-27201-1
eBook Packages: Computer ScienceComputer Science (R0)