WEARABLE DEVICE FOR SPEECH TRAINING

• US 20180108348A1
• Filed: 10/13/2016
• Published: 04/19/2018
• Est. Priority Date: 10/13/2016
• Status: Active Grant

• Current Assignee: Viesoft, Inc.
• Original Assignee: Viesoft, Inc.
• Inventors: Vierra, Anthony
• Granted Patent: US 10,304,445 B2
• Time in Patent Office: Days
• CPC Class Codes: G09B 19/04 Speaking with audible presentation of the material to be studied G09B5/04
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

A wearable utterance training system includes a wearable utterance training device. The system may, for example: (1) receive one or more target utterances from the user; (2) detect a use of one of the one or more target utterances by the user; and (3) in response, provide one or more responsive effects. The one or more responsive effects may include, for example: (1) providing one or more shocks to the user using the wearable utterance training device; (2) initiating a transfer of money between an account associated with the user and a third party account; (3) creating a public disclosure of the utterance (e.g., by posting the disclosure on one or more social media websites) and/or (4) playing a recording of the user'"'"'s use of the target utterance or other sound.

Claims

1. A wearable utterance training system, comprising:

at least one processor and memory that stores a plurality of target utterances; and

a wearable utterance training device, comprising;

a data collection device that comprises at least one microphone configured for capturing sound data; and

communication hardware for communicating the captured sound data to the at least one processor, wherein;

the at least one processor is configured for;

identifying one or more utterances of a user over a period of time;

comparing the one or more utterances of the user identified over the period of time to the plurality of target utterances;

determining that at least a particular one of the one or more utterances of the user over the period of time is one of the plurality of target utterances stored in the processor memory; and

in response to determining that the particular one of the one or more utterances of the user over the period of time is one of the plurality of target utterances stored in the processor memory, automatically providing a responsive effect based on the at least one of the one or more utterances, wherein the responsive effect is selected from a group consisting of;

(1) a positive responsive action configured to incentivize use, by the user, of the particular one of the plurality of target utterances, and (2) a negative responsive action configured to discourage use, by the user, of the particular one of the plurality of target utterances.

2. The wearable utterance training system of claim 1, wherein the at least one processor is further configured for, in response to determining that the particular one of the one or more utterances of the user over the period of time is one of the plurality of target utterances stored in the processor memory:

updating a number of times the user has uttered one of the plurality of target utterances; and

storing the number of times in the memory.

3. The wearable utterance training system of claim 1, wherein:

the wearable utterance training system further comprises a mobile computing device comprising at least one second processor;

the at least one processor is further configured for, in response to determining that the particular one of the one or more utterances of the user over the period of time is one of the plurality of target utterances stored in the processor memory, transmitting a notification of the the particular one of the one or more utterances to the mobile computing device; and

the at least one second processor is configured for, in response to receiving the notification, providing the responsive effect.

4. The wearable utterance training system of claim 3, wherein the responsive effect is selected from a group consisting of:

initiating a transfer of money between an account associated with the user and a third party account; and

creating a public disclosure to communicate information indicating that the user uttered one or more of the target utterances.

5. The wearable utterance training device of claim 1, wherein the wearable utterance training device includes a stimulus component at least indirectly.

6. The wearable utterance training device of claim 5, wherein the responsive effect comprises causing the stimulus component to initiate an electrical shock intended for the user.

7. A non-transitory computer-readable medium storing computer executable instructions for:

obtaining, by an utterance training system that includes a computing device, one or more target utterances associated with a user, wherein the one or more target utterances are known to the user and the utterance training system includes at least a wearable device at least indirectly attached to the user and a processing device that is associated with the user and is in electronic communication with the wearable device, the wearable device being an electrical device;

storing, by the utterance training system, the one or more target utterances associated with the user;

monitoring, by the utterance training system that includes a microphone for capturing sound data, the user'"'"'s utterances for a period of time;

determining, by the utterance training system, that at least a particular one of the user'"'"'s utterances during the period of time is one of the one or more target utterances; and

in response to determining that the particular one of the user'"'"'s utterances during the period of time is one of the one or more target utterances, automatically causing, by the utterance training system, a responsive effect to occur based on one at least one of the user'"'"'s utterances, wherein the responsive effect is selected from a group consisting of;

(1) a positive responsive action configured to incentivize use, by the user, of the particular one of the plurality of target utterances, and (2) a negative responsive action configured to discourage use, by the user, of the particular one of the plurality of target utterances.

8. The non-transitory computer readable medium of claim 7, wherein obtaining the one or more target utterances associated with the user comprises receiving the one or more target utterances from the user.

9. The non-transitory computer readable medium of claim 8, wherein receiving the one or more target utterances from the user comprises receiving the one or more target utterances in response to an input selected from a group consisting of:

(1) voice input to the utterance training system by the user; and

(2) text input to the utterance training system by the user.

10. The non-transitory computer readable medium of claim 7, wherein monitoring the user'"'"'s utterances for the period of time further comprises:

detecting, by the utterance training system, sound data for the period of time;

determining, by the wearable device, that a portion of the sound data comprises an utterance provided by a human voice; and

determining, by the wearable device, that the portion of the utterance provided by the human voice comprises the user'"'"'s voice.

11. The non-transitory computer readable medium of claim 10, further storing computer-executable instructions for:

converting, by the utterance training system, the portion of the utterance that was determined to be the user'"'"'s voice to utterance text;

comparing, by the utterance training system, the utterance text of the user'"'"'s voice to text of the one or more target utterances; and

determining, by the utterance training system, whether the utterance text matches the text of the one or more target utterances.

12. The non-transitory computer readable medium of claim 10, further storing computer-executable instructions for:

creating, by the utterance training system, an acoustic profile for the portion of the utterance provided by the user'"'"'s voice;

comparing, by the utterance training system, the acoustic profile for the portion of the utterance provided by the user'"'"'s voice to an acoustic profile created for each of the one or more target utterances; and

determining, by the utterance training system, whether the acoustic profile for the portion of the utterance provided by the user'"'"'s voice matches the acoustic profile for at least one of the one or more target utterances.

13. The non-transitory computer readable medium of claim 12, wherein determining that the acoustic profile for the portion of the utterance provided by the user'"'"'s voice matches the acoustic profile for at least one of the one or more identified utterances further comprises:

determining, by the utterance training system, a similarity score between the acoustic profile for the portion of the utterance provided by the user'"'"'s voice and the acoustic profile for at least one of the one or more target utterances;

comparing, by the utterance training system, the similarity score to a threshold similarity score; and

determining, by the utterance training system, whether the similarity score meets the threshold similarity score.

14. The non-transitory computer readable medium of claim 10, wherein in response to determining, by the wearable device, that the portion of the utterance provided by the human voice was not the user'"'"'s voice, disabling the responsive effect from occurring.

15. The non-transitory computer readable medium of claim 7, wherein the wearable device is selected from a group consisting of at least a necklace, a bracelet, a collar, a belt, a headband, an earring, a ring, a clasp, and a skin clamp.

16. The non-transitory computer readable medium of claim 7, wherein the responsive effect comprises an electrical vibration provided by the wearable device of the utterance training system to the user.

17. The non-transitory computer readable medium of claim 7, wherein the responsive effect is selected from a group consisting of:

a. incrementing, by the utterance training system, a number of times the user'"'"'s utterances is one or more target utterances;

b. initiating, by the utterance training system, a transfer of money between an account associated with the user and a third party account;

c. creating, by the utterance training system, a public disclosure to communicate information indicating that the user uttered one or more of the target utterances; and

d. playing, by the utterance training system, a recording of the user'"'"'s utterance that is the one or more target utterances.

18. The non-transitory computer readable medium of claim 7, wherein monitoring the user'"'"'s utterances over a period of time further comprises:

activating a microphone of a user device associated with the user; and

capturing sound data that is detected by the microphone of the user device associated with the user.

19. A computer implemented method, comprising:

obtaining, by a utterance training system that is a computing device, one or more target utterances associated with a user, wherein the one or more target utterances are known to the user and the utterance training system includes at least a wearable device at least indirectly attached to the user and a processing device that is associated with the user and is in electronic communication with the wearable device, the wearable device being an electrical device;

storing, by the utterance training system, the one or more target utterances associated with the user;

continuously monitoring, by the utterance training system, the user'"'"'s utterances for a period of time;

determining, by the utterance training system, that at least a particular one of the user'"'"'s utterances over the period of time is one of the one or more target utterances; and

in response to determining that the particular one of the user'"'"'s utterances over the period of time is one of the one or more target utterances, automatically taking an action that is a negative responsive action configured to discourage use, by the user, of the particular one of the plurality of target utterances, wherein the action is selected from a group consisting of;

a. initiating, by the utterance training system, a transfer of money between an account associated with the user and a third party account;

b. creating, by the utterance training system, a public disclosure to communicate information indicating that the user uttered one or more of the target utterances; and

c. playing, by the utterance training system, a sound.

20. The computer implemented method of claim 19, further comprising taking an action substantially immediately in response to that at least one of the user'"'"'s utterances over the period of time is one of the one or more target utterances.