Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Application of a First-Order Differential Microphone for Efficient Voice Activity Detection in a Car Platform

Agustín Álvarez, Pedro Gómez, V. Nieto, Rafael Martínez, Victoria Rodellar

Universidad Politécnica de Madrid, Spain

Handsfree interfaces provide a nice solution to add-on devices in car platforms. However, the amount of acoustic disturbances existing in automotive environments usually prevents satisfactory results. In most of the cases, noise reduction techniques involving a voice activity detector (VAD) are required. Through this paper, a robust microphone array processing technique for speech detection under the influence of noise and reverberation in an automobile environment is proposed. This method applies a simple two-microphone First Order Differential Microphone in order to estimate the power spectral density of the background perturbations embedded in speech signals. Afterwards, specialized order-statistics filters (OSFs) are applied in order to obtain a consistent speech/non speech decision. The paper also includes a performance evaluation of the algorithm using Aurora3 database recordings. According to our simulation results, the proposed algorithm shows a significantly better performance than standard VADs such as G.729B or ARM and, a slight advantage over other reported methods.

Full Paper

Bibliographic reference.  Álvarez, Agustín / Gómez, Pedro / Nieto, V. / Martínez, Rafael / Rodellar, Victoria (2005): "Application of a first-order differential microphone for efficient voice activity detection in a car platform", In INTERSPEECH-2005, 2669-2672.