| 摘要 |
<p num="1"><br/><br/><br/>Methods and apparatus to operate an audience metering device with voice <br/>commands are described herein (200). In an example method, at least one of a <br/>television program audio signal (270) or a voice command (260) from an <br/>audience member is transduced into an audio input signal (260). Based on the <br/>audio input signal and a television audio line signal (270), a residual audio <br/>signal is generated. One or more vectors from the residual audio signal are <br/>extracted (240). Based on the one or more vectors extracted from the residual <br/>audio signal, the voice command is identified (250).<br/>
|
