| abstract |
Techniques for generating summaries and action items associated with speech are described. Disclosed are techniques for presenting a first audio signal including a portion of a first audio stream at a loudspeaker, identifying data representing an audiolink associated with the first audio stream, and determining data representing a cue and data representing a second audio stream associated with the audiolink. A second audio signal including the cue may be presented, and a third audio signal including a portion of the second audio stream may be presented at the loudspeaker. |