APPARATUSES AND METHODS FOR ENHANCED SPEECH RECOGNITION IN VARIABLE ENVIRONMENTS

摘要

Systems, apparatuses, and methods are described to increase a signal-to-noise ratio difference between a main channel and reference channel. The increased signal-to-noise ratio difference is accomplished with an adaptive threshold for a desired voice activity detector (DVAD) and shaping filters. The DVAD includes averaging an output signal of a reference microphone channel to provide an estimated average background noise level. A threshold value is selected from a plurality of threshold values based on the estimated average background noise level. The threshold value is used to detect desired voice activity on a main microphone channel.

主权项

1. An integrated circuit device, comprising:
a background noise estimation module, the background noise estimation module to receive an input signal from a reference microphone, when voice activity is not detected the background noise estimation module to average the input signal from the reference microphone to form an estimated average background noise level; at least two threshold values, each of the at least two threshold values to correspond to a different estimated average background noise level; and selection logic, the selection logic to assign a particular estimated average background noise level to a threshold value from the at least two threshold values, wherein the threshold value is adapted to the particular estimated average background noise level, the threshold value is to be used by the desired voice activity detector (DVAD) to detect when desired voice activity is present.