System and method for continuous multimodal speech and gesture interaction
Disclosed herein are systems, methods, and non-transitory computer-readable storage media for processing multimodal input. A system configured to practice the method continuously monitors an audio stream associated with a gesture input stream, and detects a speech event in the audio stream. Then the system identifies a temporal window associated with a time of the speech event, and analyzes data from the gesture input stream within the temporal window to identify a gesture event. The system processes the speech event and the gesture event to produce a multimodal command. The gesture in the gesture input stream can be directed to a display, but is remote from the display. The system can analyze the data from the gesture input stream by calculating an average of gesture coordinates within the temporal window.
1. A system comprising:
a processor;
a gesture recognition module;
a speech recognition module; and
a computer-readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising:
receiving, at the speech recognition module, speech from a person within a predefined space;
identifying, by the gesture recognition module, a gesture from the person; and
generating a command based on the speech and the gesture, wherein a temporal window associated with processing the speech is either modified or unmodified from an original temporal window associated with the speech based on the gesture.
2. The system of claim 1 , wherein the predefined space comprises a medical room.
3. The system of claim 1 , wherein the gesture relates to a medical procedure.
4. The system of claim 1 , wherein the temporal window associated with processing the speech is either modified or unmodified from the original temporal window associated with the speech based a type of the gesture.
5. The system of claim 1 , wherein the gesture is associated with parameters describing specific three-dimensional characteristics of the gesture.
6. The system of claim 1 , wherein the temporal window comprises a sliding time window with a width in time that depends on a type of the gesture.
7. The system of claim 1 , wherein the gesture is chosen from a set of gestures.
8. The system of claim 1 , wherein processing the speech and the gesture comprises carrying out the command.
9. The system of claim 1 , wherein the temporal window associated with the speech and the gesture is further associated with other data separate from speech data or gesture data.
10. The system of claim 1 , wherein the gesture comprises a medical procedure gesture or a non-tactile gesture.
11. A method comprising:
receiving, at a speech recognition module configured on a computing device, speech from a person within a predefined space;
identifying, by a gesture recognition module of the computing device, a gesture from the person; and
generating, via a processor of the computing device, a command based on the speech and the gesture, wherein a temporal window associated with processing the speech is either modified or unmodified from an original temporal window associated with the speech based on the gesture.
12. The method of claim 11 , wherein the redefined space comprises a medical room.
13. The method of claim 11 , wherein the gesture relates to a medical procedure.
14. The method of claim 11 , wherein the temporal window associated with processing the speech is either modified or unmodified from the original temporal window associated with the speech based a type of the gesture.
15. The method of claim 11 , wherein the gesture is associated with parameters describing specific three-dimensional characteristics of the gesture.
16. The method of claim 11 , wherein the temporal window comprises a sliding time window with a width in time that depends on a type of the gesture.
17. The method of claim 11 , wherein the gesture is chosen from a set of gestures.
18. The method of claim 11 , wherein processing the speech and the gesture comprises carrying out the command.
19. The method of claim 11 , wherein the temporal window associated with the speech and the gesture is further associated with other data separate from speech data or gesture data.
20. The method of claim 11 , wherein the gesture comprises a medical procedure gesture or a non-tactile gesture.