Detecting repetitions in audio data

1. A system for processing audio, the system comprising:

one or more audio sensors included in a wearable apparatus; and

at least one processing unit configured to:

capture audio data from an environment of a wearer of the wearable apparatus using the one or more audio sensors;

analyze the audio data to detect a repetition in the audio data, the repetition comprises a first occurrence of a repeated element followed by one or more successive occurrences of the repeated element;

analyze the audio data to determine whether the repetition is socially acceptable;

analyze the audio data to determine that the repeated element is a sentence;

analyze the audio data to determine which of the one or more successive occurrences of the repeated element were produced by the wearer; and

when the repetition is not socially acceptable, the repeated element is a sentence and all of the one or more successive occurrences of the repeated element were produced by the wearer, provide a feedback to a user.

2. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to obtain textual information; and

analyze the obtained textual information to determine whether the repetition is socially acceptable.

3. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to determine whether the repetition is meaningful; and

when the repetition is not socially acceptable, the repeated element is a sentence, the repetition is meaningless and all of the one or more successive occurrences of the repeated element were produced by the wearer, provide a feedback to the user.

4. The system of claim 1 , wherein the at least one processing unit is further configured to provide a feedback to the user when the repetition is not socially acceptable, the repeated element is a sentence, the first occurrence of a repeated element was produced by the wearer, and all of the one or more successive occurrences of the repeated element were produced by the wearer.

5. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to count a number of occurrences of the repeated element in the repetition; and

when the repetition is not socially acceptable, the repeated element is a sentence, the number of occurrences of the repeated element exceeds a particular threshold and all of the one or more successive occurrences of the repeated element were produced by the wearer, provide a feedback to the user.

6. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to measure a time length of the one or more successive occurrences; and

when the repetition is not socially acceptable, the repeated element is a sentence, the time length of the one or more successive occurrences exceeds a particular threshold, and all of the one or more successive occurrences of the repeated element were produced by the wearer, provide a feedback to the user.

7. The system of claim 1 , wherein the at least one processing unit is further configured to:

when the repetition is not socially acceptable, the repeated element is a sentence, the first occurrence of a repeated element was not produced by the wearer and all of the one or more successive occurrences of the repeated element were produced by the wearer, provide a feedback to the user.

8. The system of claim 1 , wherein the user is the wearer of the wearable apparatus.

9. The system of claim 1 , wherein the user is a caregiver of the wearer of the wearable apparatus.

10. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to measure a time length of the one or more successive occurrences; and

control an intensity of the feedback based on the measured time length.

11. The system of claim 1 , wherein the at least one processing unit is further configured to select a content of the feedback based on the type of the repeated element.

12. The system of claim 1 , wherein the at least one processing unit is further configured to:

after providing the feedback, identify additional occurrences of the repeated element; and

after at least a selected minimal number of additional repetitions of the repeated element are identified, provide an additional feedback to the user.

13. The system of claim 1 , wherein the at least one processing unit is further configured to:

aggregate information related to one or more identified properties of the detected repetition and of one or more additional repetitions; and

generate a report based on the aggregated information, the report comprises statistical information related to the one or more identified properties.

14. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to obtain prosodic information associated with speech rhythm; and

control a nature of the feedback based on the prosodic information.

15. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to obtain prosodic information associated with speech tempo; and

control a nature of the feedback based on the prosodic information.

16. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to obtain prosodic information associated with pitch of voice; and

control a nature of the feedback based on the prosodic information.

17. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to obtain prosodic information associated with loudness of voice; and

control a nature of the feedback based on the prosodic information.

18. The system of claim 1 , wherein the at least one processing unit is further configured to:

analyze the audio data to obtain prosodic information associated with intonation of voice; and

control a nature of the feedback based on the prosodic information.

19. A non-transitory computer readable medium storing data and computer implementable instructions for carrying out a method for processing audio, the method comprising:

obtaining audio data captured by one or more audio sensors included in a wearable apparatus from an environment of a wearer of the wearable apparatus;

analyzing the audio data to detect a repetition in the audio data, the repetition comprises a first occurrence of a repeated element followed by one or more successive occurrences of the repeated element;

analyzing the audio data to determine whether the repetition is socially acceptable;

analyzing the audio data to determine that the repeated element is a sentence;

analyzing the audio data to determine which of the one or more successive occurrences of the repeated element were produced by the wearer; and

when the repetition is not socially acceptable, the repeated element is a sentence and all of the one or more successive occurrences of the repeated element were produced by the wearer, providing a feedback to a user.

20. A method for processing audio, the method comprising:

obtaining audio data captured by one or more audio sensors included in a wearable apparatus from an environment of a wearer of the wearable apparatus;

analyzing the audio data to detect a repetition in the audio data, the repetition comprises a first occurrence of a repeated element followed by one or more successive occurrences of the repeated element;

analyzing the audio data to determine whether the repetition is socially acceptable;

analyzing the audio data to determine that the repeated element is a sentence;

analyzing the audio data to determine which of the one or more successive occurrences of the repeated element were produced by the wearer; and

when the repetition is not socially acceptable, the repeated element is a sentence and all of the one or more successive occurrences of the repeated element were produced by the wearer, providing a feedback to a user.