A method and apparatus for selective speech recognition includes receiving
a media file (112) having a media type indicator (114). The method and
apparatus further includes a browser (104) that receives the media file
and a speech recognition engine selector (106) that receives the media
type indicator from the browser (104). The selected speech recognition
engine selector (106) then selects either a first speech recognition
engine (108) or a second speech recognition engine (110), in response to
the media type indicator. The method and apparatus further includes an
audio receiver (102) that receives an audio input (116) which is provided
to the enabled first speech recognition engine (108) or the second speech
recognition engine (110), thereupon allowing for the reduction in power
consumption by disabling a speech recognition engine (108 or 110) until
actively selected by the speech recognition engine selector (106).
