US 12,073,821 B2
System and methodology for modulation of dynamic gaps in speech
Zohar Sherman, Kerem Maharal (IL); and Ori Inbar, Ramat Gan (IL)
Assigned to IGENTIFY LTD., Tirat Hacarmel (IL)
Appl. No. 17/428,528
Filed by IGENTIFY LTD., Tirat HaCarmel (IL)
PCT Filed Jan. 30, 2020, PCT No. PCT/IL2020/050117
§ 371(c)(1), (2) Date Aug. 4, 2021,
PCT Pub. No. WO2020/161697, PCT Pub. Date Aug. 13, 2020.
Claims priority of provisional application 62/801,158, filed on Feb. 5, 2019.
Prior Publication US 2022/0189500 A1, Jun. 16, 2022
Int. Cl. G10L 13/10 (2013.01); G06N 20/00 (2019.01); G10L 13/02 (2013.01); G10L 21/045 (2013.01); G10L 21/055 (2013.01)
CPC G10L 13/10 (2013.01) [G06N 20/00 (2019.01); G10L 13/02 (2013.01); G10L 21/045 (2013.01); G10L 21/055 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system configured for speech gap modulation, comprising a processing circuitry configured to:
(a) receive at least one composite speech portion, wherein the at least one composite speech portion comprises at least one speech portion and a plurality of dynamic-gap portions,
wherein the at least one speech portion comprises at least one variable-value speech portion,
wherein the plurality of dynamic-gap portions are associated with pauses in speech,
wherein at least one dynamic-gap portion of the plurality of dynamic-gap portions is associated with a dynamic-gap type of a plurality of dynamic-gap types,
wherein at least one other dynamic-gap portion of the plurality of dynamic-gap portions is associated with another dynamic-gap type of a plurality of dynamic-gap types, the dynamic-gap type and the other dynamic-gap type being distinct,
wherein each dynamic-gap type of the plurality of dynamic-gap types is associated with a corresponding minimum gap playback time of a plurality of minimum gap playback times,
wherein the each dynamic-gap type is associated with a corresponding maximum gap playback time of a plurality of maximum gap playback times;
(b) receive at least one synchronization point, wherein the at least one synchronization point is associating a point in time in the at least one composite speech portion and a point in time in at least one other media portion; and
(c) modulate at least one dynamic-gap portion of the plurality of dynamic-gap portions, based at least partially on the at least one variable-value speech portion, and on the at least one synchronization point, thereby generating at least one modulated composite speech portion,
wherein the modulation of the least one dynamic-gap portion comprises at least one of increasing a gap playback time, associated with the at least one dynamic-gap portion, and decreasing the gap playback time,
wherein the increasing of the gap playback time is limited by the corresponding maximum playback time,
wherein the decreasing of the gap playback time is limited by the corresponding minimum playback time,
thereby facilitating improved synchronization of the at least one modulated composite speech portion and the at least one other media portion at the at least one synchronization point, when combining the at least one other media portion and the audio-format modulated composite speech portion into a synchronized multimedia output.