Method and apparatus for voice modification during a call
View Patent ↗A method for voice modification during a telephone call comprising receiving a source audio signal associated with at least one participant, wherein the source audio signal comprises a voice of the at least one participant, detecting a source dialect of the at least one participant, selecting a target dialect based on at least a characteristic of a target participant and creating a modulated audio signal based on the source audio signal, the source dialect, and the target dialect and transmitting the modulated audio signal to the target participant.
1. A method for voice modification during a call comprising:
retrieving participant metadata for a first participant of the call, wherein the participant metadata includes information regarding a target dialect used in previous calls associated with the first participant;
creating a modulated audio signal based on a source audio signal of a second participant and the target dialect;
analyzing the modulated audio signal of the second participant to determine whether the modulation was successful;
adjusting the modulation when the modulation is not successful; and
transmitting the modulated audio signal to the first participant.
2. The method of claim 1 , wherein the participant metadata is stored in a user profile associated with the first participant.
3. The method of claim 2 , wherein a unique identifier of the first participant is used as a lookup key to locate the user profile associated with the first participant.
4. The method of claim 3 , wherein the unique identifier of the first participant is one of a caller ID, messaging system identifier, email address, account identifier, or IP address of the first participant.
5. The method of claim 1 , wherein creating a modulated audio signal comprises:
converting the audio signal associated with the second participant to a source text;
selecting a speech profile based on metadata associated with the first participant;
transforming the source text into modified text based on the speech profile; and
converting the modified text to speech, based on the selected speech profile.
6. A method for voice modification during a call, comprising:
retrieving participant metadata for a first participant of the call, wherein the participant metadata includes information regarding a target dialect used in previous calls associated with the first participant;
creating a modulated audio signal based on a source audio signal of a second participant and the target dialect;
transmitting the modulated audio signal to the first participant; and
determining whether the modulation was successful based on feedback from the at least one the first or second participant.
7. A method for voice modification during a call comprising:
retrieving participant metadata for a first participant of the call, wherein the participant metadata includes at least one of (A) a first target dialect selected by the first participant to be applied to a source audio signal of the first participant or (B) a second target dialect selected by the first participant to be applied to source audio signals of other participants of the call;
creating a modulated audio signal based on at least one of the first target dialect and the source audio signal of the first participant, or the second target dialect and the source audio signal of the other participants of the call;
analyzing the modulated audio signal to determine whether the modulation was successful;
adjusting the modulation when the modulation is not successful; and
transmitting the modulated audio signal to the participants of the call.
8. The method of claim 7 , wherein the participant metadata is stored in a user profile associated with the first participant.
9. The method of claim 8 , wherein a unique identifier of the first participant is used as a lookup key to locate the user profile associated with the first participant.
10. The method of claim 9 , wherein the unique identifier of the first participant one of a caller ID, messaging system identifier, email address, account identifier, or IP address of the first participant.
11. The method of claim 7 , further comprising:
further determining whether the modulation was successful based on feedback from at least one of the participants.
12. A method for routing a call, comprising:
determining a dialect of a first participant of the call, wherein the dialect of the first participant is one of retrieved from participant metadata associated with the first participant, or detected via a dialect detection analysis of an audio signal associated with the first participant;
routing the call to a second participant of the call based on the determined dialect of the first participant;
creating a modulated audio signal based on a source audio signal of the second participant and the determined dialect of the first participant;
analyzing the modulated audio signal to determine whether the modulation was successful;
adjusting the modulation when the modulation is not successful; and
transmitting the modulated audio signal to the first participant.
13. The method of claim 12 , further comprising:
further determining whether the modulation was successful based on feedback from at least one of the participants.