Abstract: Systems and methods for generating audio data in accordance with embodiments of the invention are illustrated. One embodiment includes a method for generating audio data. The method includes steps for generating a plurality of style tokens from a set of audio inputs, generating an input feature vector based on the plurality of style tokens and a set of text features, and generating audio data (e.g., a spectrogram, audio waveforms, etc.) based on the input feature vector.
Type:
Application
Filed:
June 24, 2020
Publication date:
December 24, 2020
Applicant:
Replicant Solutions, Inc.
Inventors:
Zak Semenov, John Meade, Alessandro Marin, Alexander L. De Souza, Benjamin Gleitzman, Meghna Suresh
Abstract: Systems and methods for managing a call between a contact, a conversation bot, and a human agent are disclosed. The method selects a conversation bot associated with a particular human agent from multiple conversation bots that are each associated with a different human agent. Each conversation bot can be a model trained using conversation data recorded during conversations conducted by the particular human agent with which it is associated. The method connects an audio call with a human contact, and generates audio during the call based upon a voice of the particular human agent. The method determines that a transition criterion is satisfied, and selects a selected human agent from amongst a plurality of available human agents. When the transition criterion is satisfied, the method enables a selected human agent to participate on the call, and continues the call between the selected human agent and the human contact.
Type:
Grant
Filed:
June 22, 2018
Date of Patent:
June 23, 2020
Assignee:
Replicant Solutions, Inc.
Inventors:
Jack Phillip Abraham, Benjamin Gleitzman