| 摘要 |
A speech driven control system for controlling the rate at which a pre-prepared text is to be displayed comprising: an audio input connected to receive an audio signal representing speech delivered by the speaker, said speech intended to match said pre-prepared text; means for converting the signal into observations; a data structure representing said pre-prepared text as a plurality of phonemes; means for comparing observations derived from the audio signal with phonemes in the data structure to determine at any time the location in the text represented by the speech delivered by the speaker; and means for generating a display control signal for controlling the rate at which text is displayed based on the determined location. |
