Privacy generation

• US 9,094,509 B2
• Filed: 06/28/2012
• Issued: 07/28/2015
• Est. Priority Date: 06/28/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Barillaud, Franck, Dutta, Shiv, Mendoza, Alfredo V, Arenburg, Robert T
• Primary Examiner(s): Han, Qi
• Application Number:
  US13/536,483
• Publication Number:
  US 20140003596A1
• Time in Patent Office: 1,125 Days
• Field of Search: 704/273, 704/276, 704/278, 704/206, 704/226, 704/260, 704/266
• US Class Current: 1/1
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 15/25 using position of the lips, movement of the lips or face analysis
• CPC Class Codes: H04M 2242/10 Secret communications
• CPC Class Codes: H04M 3/42391 where the subscribers are hearing-impaired persons, e.g. telephone devices for the deaf

Abstract

For generating privacy, a detection module detects an optical lingual cue from user speech that comprises an audible signal. A generation module transmits an inverse audible signal generated from the optical lingual cue.

Claims

1. A method for privacy generation comprising:

detecting, by use of a processor, a training optical lingual cue in response to a user reading a training text;

receiving a training audible signal in response to the user reading the training text;

generating a speech model from the training optical lingual cue and the training audible signal, the speech model associating at least one training optical lingual cue with at least one phoneme;

detecting, based on the speech model, one or more optical lingual cues from user speech that comprises an audible signal;

generating a simulated signal from the speech model and the one or more optical lingual cues by selecting at least one phoneme from the speech model that corresponds to the one or more optical lingual cues;

transmitting the simulated signal;

generating an inverse audible signal from the simulated signal, the inverse audible signal having a frequency response of the simulated signal with an amplitude inverse of the amplitude of the simulated signal; and

transmitting the inverse audible signal.

2. The method of claim 1, further comprising:

receiving combined audible signals; and

updating the speech model from the combined audible signals.

3. The method of claim 2, wherein the combined audible signals are received from a direction microphone.

4. The method of claim 1, the optical lingual cue comprising at least one of positions and movements of the lips, mouth, and tongue, throat vibrations, and facial movements.

5. The method of claim 1, wherein the transmitted inverse audible signal anticipates the audible signal by a specified time interval.

6. The method of claim 1, wherein the inverse audible signal is directional.

7. A computer program product for privacy generation, the computer program product comprising a computer readable storage medium having computer readable program code embodied therein, the computer readable program code configured to:

detect a training optical lingual cue in response to a user reading a training text;

receive a training audible signal in response to the user reading the training text;

generate a speech model from the training optical lingual cue and the training audible signal, the speech model associating at least one training optical lingual cue with at least one phoneme;

detect, based on the speech model, one or more optical lingual cues from user speech that comprises an audible signal;

generate a simulated signal from the speech model and the one or more optical lingual cues by selecting at least one phoneme from the speech model that corresponds to the one or more optical lingual cues;

transmit the simulated signal;

generate an inverse audible signal from the simulated signal, the inverse audible signal having a frequency response of the simulated signal with an amplitude inverse of the amplitude of the simulated signal; and

transmit the inverse audible signal.

8. The computer program product of claim 7, the computer readable program code further:

receiving combined audible signals; and

updating the speech model from the combined audible signals.

9. The computer program product of claim 8, wherein the combined audible signals are received from a direction microphone.

10. The computer program product of claim 7, the optical lingual cue comprising at least one of positions and movements of the lips, mouth, and tongue, throat vibrations, and facial movements.

11. The computer program product of claim 7, wherein the transmitted inverse audible signal anticipates the audible signal by a specified time interval.

12. The computer program product of claim 7, wherein the inverse audible signal is directional.

13. A system comprising:

a telephone comprising;

a detection module that detects a training optical lingual cue in response to a user reading a training text and receives a training audible signal in response to the user reading the training text, the detection module generating a speech model from the training optical lingual cue and the training audible signal, the speech model associating at least one training optical lingual cue with at least one phoneme, the detection module further detecting, based on the speech model, one or more optical cues from user speech that comprises an audible signal; and

a generation module that generates a simulated signal from the speech model and the one or more optical lingual cues by selecting at least one phoneme from the speech model that corresponds to the one or more optical lingual cues, the generation module transmitting the simulated signal and generating an inverse audible signal from the simulated signal, the inverse audible signal having a frequency response of the simulated signal with an amplitude inverse of the amplitude of the simulated signal, the generation module transmitting the inverse audible signal.

14. The system of claim 13, the generation module further receiving combined audible signals and updating the speech model from the combined audible signals.