Noise estimation in speech recognition

摘要

A noise reduction function (235) has a Wiener Filter (335) with adjustable filter coefficients. Multiple microphones (142, 144) are configured to provide a substantially continuous noise signal to a noise spectrum estimation function (325) to provide a substantially continuous estimate of noise. The noise estimate is used to adjust the filter coefficients of the Wiener Filter (335) , thereby removing noise from the noisy speech. By using the noise estimate from a microphone array, the Wiener filter coefficients can be updated substantially continuously, for example, each speech frame. This enables the noise to be tracked more closely than in known techniques.