Granted Patent B2

US 12,340,808 · App. 18/180,364 · Granted Jun 24, 2025

Inventors: Aviad Maizels (Ramat Hasharon, IL); Avi Barliya (Tel Aviv, IL); Yonatan Wexler (Jerusalem, IL)

Assignee: Q (Cue) Ltd.

G10L15/26G02B27/0093G06F40/58G06V10/141G06V10/60G06V10/82G06V40/171G06V40/174G06V40/176G10L13/02G10L13/027G10L13/04G10L15/16G10L15/25G06F3/015

Abstract

Claims (33)

1. A system for determining intended speech based on minute facial skin movements, the system comprising:

a housing;

at least one sensor connected to the housing in a manner such that when the housing is worn, the at least one sensor is held at a distance from a skin surface;

at least one processor configured to:

control at least one coherent light source to project a plurality of light spots on a region of a face;

receive from the at least one sensor, reflection signals indicative of coherent light reflected from at least a subset of the plurality of light spots projected on the region of the face;

analyze the reflection signals to determine minute facial skin movements indicative of the intended speech;

based on the determined minute facial skin movements indicative of the intended speech, extract words corresponding to the intended speech; and

initiate, prior to an audible utterance of the intended speech, an action based on the extracted words.

2. The system of claim 1 , wherein the initiated action includes removing background noises from captured audio signals.

3. The system of claim 1 , wherein the initiated action involves engaging with a virtual personal assistant.

4. The system of claim 1 , wherein the initiated action involves initiating a phone call.

5. The system of claim 1 , wherein the initiated action involves translating the extracted words.

6. The system of claim 5 , wherein translating the extracted words involves determining conversation context of the intended speech.

7. The system of claim 5 , wherein translating includes transcribing the extracted words to text.

8. The system of claim 5 , wherein translating includes generating a translated utterance in a synthesized voice and in a language other than a language of the extracted words.

9. The system of claim 8 , wherein the at least one processor is further configured to output the translated utterance.

10. The system of claim 9 , wherein the at least one processor is configured to generate the translated utterance before occurrence of a corresponding voiced utterance, and to output the translated utterance at a time of the voiced utterance.

11. The system of claim 1 , wherein the at least one processor is configured to perform the initiated action in an absence of vocalization of the extracted words or utterance of any other sounds.

12. The system of claim 1 , wherein the action includes extracting multiple candidate phonemes together with respective probabilities, and synthesizing audible speech responsively to the extracted phonemes.

13. The system of claim 12 , wherein synthesizing the audible speech includes mixing the multiple candidate phonemes based on their respective probabilities.

14. The system of claim 1 , wherein the housing is configured for engagement with an ear of a user.

15. The system of claim 14 , wherein the at least one processor is included in the wearable housing and is configured to transmit data associated with the intended speech to a mobile communications device via a communication link.

16. The system of claim 15 , wherein the at least one processor is configured to determine the intended speech for presentation by the mobile communications device.

17. The system of claim 1 , wherein the at least one processor is configured to acquire the reflection signals at an acquisition rate lower than 200 samples per second.

18. The system of claim 1 , wherein the plurality of light spots projected on the region of the face illuminate an area of at least 1 cm 2 .

19. The system of claim 1 , wherein the at least one processor is configured to select the subset of the spots and extract temporal and/or spectral features of the coherent light in the selected subset of the spots.

20. A method for determining intended speech based on minute movements of facial skin surface, the method comprising:

controlling at least one coherent light source to project a plurality of light spots on a region of a face;

receiving from at least one sensor held at a distance from a skin surface, reflection signals indicative of coherent light reflected from at least a subset of the plurality of light spots projected on the region of the face;

analyzing the reflection signals to determine minute facial skin movements indicative of the intended speech;

based on the determined minute facial skin movements indicative of the intended speech, extracting words corresponding to the intended speech; and

initiate, prior to an audible utterance of the intended speech, an action based on the extracted words.

Assignments (3)

Continuity (4)

References Cited (249)