A two-microphone diversity system and its application for hands-free car kits
نویسندگان
چکیده
In this paper we consider a two-channel diversity technique that combines the processed signals of two separate microphones. For in-car applications, this enables a better compromise for the microphone positions. The advantage of the proposed system is its insensitivity with respect to varying speaker sizes or local noise sources. To achieve this we choose the microphone position in that way that one microphone is optimum for a tall speaker, and the second one is suitable for a small speaker. For local noise sources we may apply a similar design to choose the microphone position in accordance with the location of the noise sources. A corresponding signal combiner has to tasks: compensation of phase shifts and weighting proportional to the signal strength. We propose solutions for both problems and demonstrate the effectiveness of diversity combining.
منابع مشابه
A Two-Sensor Noise Reduction System: Applications for Hands-Free Car Kit
This paper presents a two-microphone speech enhancer designed to remove noise in hands-free car kits. The algorithm, based on the magnitude squared coherence, uses speech correlation and noise decorrelation to separate speech from noise. The remaining correlated noise is reduced using cross-spectral subtraction. Particular attention is focused on the estimation of the different spectral densiti...
متن کاملOptimum Microphone Array for Hands-free Devices in a Car
Nowadays, hands-free devices for cars is a hot technology that evolves very fast, providing new and advanced features to the users. However, the speech quality in such devices can be significantly degraded by different types of noise and interfering signals, having stronger impact in the person listening the speech acquired inside the car. Microphone arrays enable noise reduction by means of be...
متن کاملCENSREC2: corpus and evaluation environments for in car continuous digit speech recognition
This paper introduces a common database and an evaluation framework for connected digit speech recognition in real driving car environments, CENSREC-2, as an outcome of IPSJ-SIG SLP Noisy Speech Recognition Evaluation Working Group. Speech data of CENSREC-2 was collected using two microphones, a close-talking microphone and a hands-free microphone, under three car speeds and four car conditions...
متن کاملRobust Superdirectional Beamforming for Hands-Free Speech Capture in Cars
The application of multichannel signal processing algorithms in front-ends of hands-free speech communication systems facilitates a better extraction of a desired source signal and allows for a suppression of unwanted noise and interference in car interiors. In this paper, a novel superdirective beamforming design method called the Robust Least-Squares Frequency-Invariant Beamformer (RLSFIB) is...
متن کاملBlind Source Separation for Speech Application Under Real Acoustic Environment
A hands-free speech recognition system [1] is essential for the realization of an intuitive, unconstrained, and stress-free human-machine interface, where users can talk naturally because they require no microphone in their hands. In this system, however, since noise and reverberation always degrade speech quality, it is difficult to achieve high recognition performance, compared with the case ...
متن کامل