Systems and methods for filtering unwanted sounds from a conference call using voice synthesis

1. A method comprising:

capturing a first voice signal, the first voice signal comprising a voice of a first user and a voice of a second user, by a first device, during a conference call;

converting the first voice signal into corresponding text;

analyzing the text to determine that a first portion of the text was spoken by the first user, and a second portion of text was spoken by the second user;

determining whether the first user is relevant to the conference call, and whether the second user is relevant to the conference call; and

in response to determining that the first user is relevant to the conference call, and that the second user is not relevant to the conference call:

preventing the first voice signal, the first voice signal comprising the voice of the first user and the voice of the second user, from being transmitted into the conference call;

converting the first portion of the text to a second voice signal; and

transmitting the second voice signal into the conference call.

2. The method of claim 1 , wherein the second portion of the text is not converted to a voice signal and is not transmitted into the conference call.

3. The method of claim 1 , wherein converting the first portion of the text into a second voice signal comprises:

retrieving a voice profile of the first user; and

synthesizing the first portion of the text into a voice of the first user based on the voice profile.

4. The method of claim 1 , wherein determining whether the first user is relevant to the conference call and whether the second user is relevant to the conference call comprises:

retrieving a first user profile of the first user and a second user profile of the second user; identifying a subject of the conference call;

determining, based on the first user profile, whether the first user is familiar with the subject of the conference call; and

determining, based on the second user profile, whether the second user is familiar with the subject of the conference call.

5. The method of claim 1 , wherein determining whether the first user is relevant to the conference call and whether the second user is relevant to the conference call comprises:

identifying a first account associated with the first user;

identifying a second account associated with the second user;

determining whether the first account received an invitation to the conference call; and

determining whether the second account received an invitation to the conference call.

6. The method of claim 1 , further comprising converting the second portion of the text to a second voice signal by:

retrieving a voice profile of the second user; and

synthesizing the second portion of the text into a voice of the second user based on the voice profile.

7. The method of claim 1 , wherein the preventing the first voice signal, the first voice signal comprising the voice of the first user and the voice of the second user, from being transmitted into the conference call further comprises:

preventing transmission into the conference call of all voices present in the first voice signal.

8. The method of claim 1 , further comprising:

converting the second portion of the text to a third voice signal;

transmitting the third voice signal into the conference call separately from the second voice signal; and

presenting, to other participants in the conference call, an option to select whether to listen to the second voice signal or the third voice signal.

9. A system comprising:

audio input circuitry configured to capture voice signals; and

control circuitry configured to:

capture, using the audio input circuitry, a first voice signal, the first voice signal comprising a voice of a first user and a voice of a second user, during a conference call;

convert the first voice signal into corresponding text;

analyze the text to determine that a first portion of the text was spoken by the first user, and a second portion of text was spoken by the second user;

determine whether the first user is relevant to the conference call, and whether the second user is relevant to the conference call; and

in response to determining that the first user is relevant to the conference call, and that the second user is not relevant to the conference call:

prevent the first voice signal, the first voice signal comprising the voice of the first user and the voice of the second user, from being transmitted into the conference call;

convert the first portion of the text to a second voice signal; and

transmit the second voice signal into the conference call.

10. The system of claim 9 , wherein the second portion of the text is not converted to a voice signal and is not transmitted into the conference call.

11. The system of claim 9 , wherein the control circuitry configured to convert the first portion of the text into a second voice signal is further configured to:

retrieve a voice profile of the first user; and

synthesize the first portion of the text into a voice of the first user based on the voice profile.

12. The system of claim 9 , wherein the control circuitry configured to determine whether the first user is relevant to the conference call and whether the second user is relevant to the conference call is further configured to:

retrieve a first user profile of the first user and a second user profile of the second user;

identify a subject of the conference call;

determine, based on the first user profile, whether the first user is familiar with the subject of the conference call; and

determine, based on the second user profile, whether the second user is familiar with the subject of the conference call.

13. The system of claim 9 , wherein the control circuitry configured to determine whether the first user is relevant to the conference call and whether the second user is relevant to the conference call is further configured to:

identify a first account associated with the first user;

identify a second account associated with the second user;

determine whether the first account received an invitation to the conference call; and

determine whether the second account received an invitation to the conference call.

14. The system of claim 9 , wherein the control circuitry is further configured to convert the second portion of the text to a second voice signal by:

retrieving a voice profile of the second user; and

synthesizing the second portion of the text into a voice of the second user based on the voice profile.

15. The system of claim 9 , wherein the control circuitry is further configured to, when preventing the first voice signal, the first voice signal comprising the voice of the first user and the voice of the second user, from being transmitted into the conference call, prevent transmission into the conference call of all voices present in the first voice signal.

16. The system of claim 9 , wherein the control circuitry is further configured to:

convert the second portion of the text to a third voice signal;

transmit the third voice signal into the conference call separately from the second voice signal; and

present, to other participants in the conference call, an option to select whether to listen to the second voice signal or the third voice signal.

17. A system comprising:

means for capturing a first voice signal, the first voice signal comprising a voice of a first user and a voice of a second user, by a first device, during a conference call;

means for converting the first voice signal into corresponding text;

means for analyzing the text to determine that a first portion of the text was spoken by the first user, and a second portion of text was spoken by the second user;

means for determining whether the first user is relevant to the conference call, and whether the second user is relevant to the conference call; and

means for, in response to determining that the first user is relevant to the conference call, and that the second user is not relevant to the conference call:

preventing the first voice signal, the first voice signal comprising the voice of the first user and the voice of the second user, from being transmitted into the conference call;

converting the first portion of the text to a second voice signal; and

transmitting the second voice signal into the conference call.

18. The system of claim 17 , wherein the second portion of the text is not converted to a voice signal and is not transmitted into the conference call.

19. The system of claim 17 , wherein the means for converting the first portion of the text into a second voice signal comprises:

means for retrieving a voice profile of the first user; and

means for synthesizing the first portion of the text into a voice of the first user based on the voice profile.

20. The system of claim 17 , wherein the means for determining whether the first user is relevant to the conference call and whether the second user is relevant to the conference call comprises:

means for retrieving a first user profile of the first user and a second user profile of the second user;

means for identifying a subject of the conference call;

means for determining, based on the first user profile, whether the first user is familiar with the subject of the conference call; and

means for determining, based on the second user profile, whether the second user is familiar with the subject of the conference call.