Robust speech recognition in a vehicular environment has been an important research field that has attracted great research interest in recent years. Performance of general-purpose speech recognizers dramatically degrade because of various kinds of prevailing noise sources in cars. To deal with acoustic noises, we have proposed two noise reduction systems based on microphone array and post-filtering. In this chapter, we first describe these two noise reduction systems. Then, we present our investigation into the performance improvements of the automatic speech recognition (ASR) system for in-car applications when the two noise reduction systems are used as the front-end processors. We report the speech recognition experiments we have conducted using car noise recordings and the AURORA-2J speech database, as well as the recognition results we have obtained. Finally, based on these experimental results, we present some discussions on the proposed noise reduction systems.
CITATION STYLE
Li, J., & Akagi, M. (2007). Noise reduction based on microphone array and post-filtering for robust speech recognition in car environments. In Advances for In-Vehicle and Mobile Systems: Challenges for International Standards (pp. 153–166). Springer Science and Business Media, LLC. https://doi.org/10.1007/978-0-387-45976-9_13
Mendeley helps you to discover research relevant for your work.