Alteration of speech within an audio stream based on a characteristic of the speech

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

• one or more instructions that, when executed by one or more processors of a system, cause the system to:
• receive an audio stream associated with a call between a user and an individual;
• process, using a speech analysis model, user speech within the audio stream that is associated with the user to identify a user accent associated with the user,
• wherein the user accent is a first type of accent, and
• wherein the speech analysis model is trained to identify a type of accent based on:
• reference speech data that indicates inflection points associated with the first type of accent for words of a language and corresponding inflection points associated with a second type of accent for the words, and
• reference audio data that indicates audio characteristics of respective inflection points of multiple accents associated with the first type of accent and corresponding audio characteristics of respective inflection points of multiple accents associated with the second type of accent;
• determine whether an accent characteristic of the user is different from an accent characteristic of the individual based on a comparison of the accent characteristic of the user and the accent characteristic of the individual;
• process, using a speech alteration model and based on determining whether the accent characteristic of the user is different from the accent characteristic of the individual, the audio stream to alter speech of the individual, within the audio stream, that has the second type of accent,
• wherein the speech alteration model is configured to form, from the speech, altered speech associated with the individual and that has the first type of accent, and wherein the speech alteration model is trained based on the reference audio data and the reference speech data;
• replace, within a user channel of the audio stream, the speech with the altered speech;
• and
• provide, via the user channel, the altered speech to the user.

A method for altering speech of a speaker in an audio stream, comprising:

• receiving, by a device, an audio stream associated with a call between a user and an individual;
• identifying, by the device and using a model, an accent characteristic of the individual based on speech within the audio stream, wherein the model is trained to identify an accent characteristic based on:
• reference speech data that indicates inflection points associated with an accent characteristic of the user for words of a language and corresponding inflection points associated with the accent characteristic of the individual for the words, and
• reference audio data that indicates audio characteristics of respective inflection points of multiple accents associated with the accent characteristic of the user and corresponding audio characteristics of respective inflection points of multiple accents associated with the accent characteristic of the individual;
• determining whether the accent characteristic of the user is different from the accent characteristic of the individual based on a comparison of the accent characteristic of the user and the accent characteristic of the individual;
• processing, by the device and based on determining whether the accent characteristic of the user is different from the accent characteristic of the individual, the speech from a first channel of the audio stream to alter the speech from having a first speech characteristic corresponding to an accent of the individual to having a second speech characteristic corresponding to an accent of the user,
• wherein a speech alteration model for altering the speech is trained based on the reference audio data and based on the reference speech data;
• extracting, by the device, the speech from the first channel that has the first speech characteristic;
• and
• providing, by the device and within a second channel of the audio stream, altered speech that corresponds to the speech and that has the second speech characteristic.