Description:This patent incorporates real-time voice codec adaptation to devote more bits to important speech. Adjusting the bitrate based on inferred value of each frame. Frame importance is predicted based on models of dialog dynamics. No assumption that all speech is equally valuable. Current voice codes adapt to channel characteristics, but lack any adaptation to importance, communicative value, or dialog/reverence. Speech importance increases from less important silence, in-breaths, fillers ("Um", "Well"), back channels ("Uh-huh"), disfluencies, false starts, and repetitions, to more important normal and critical content. Patent issued.
Abstract:A method, system, and computer-usable non-transitory storage device for dynamic voice codec adaptation are disclosed. The voice codec adapts in real time to devote more bits to audio quality when it is most needed, and fewer bits to less important parts of utterances are disclosed. Dialog knowledge is utilized for compression opportunities to adjust the bitrate moment-by-moment, based on the inferred value of each frame. Frame importance and appropriate transmission fidelity is predicted based on prosodic features and models of dialog dynamics. This technique provides the same communications quality with less spectrum needs, fewer antennas, and less battery drain.
Issue Date: 12/08/2015
Application Date: 04/08/2013
Post Date: 03/02/2018
UTEP Docket No: 2012-009
