Voice Profile Sharing via Authorization Profiles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice-to-text (TTS) templates in cloud computing are difficult to share and utilize by multiple recipients, limiting their accessibility and collaboration.

Innovation Solution

A method and system for generating and sharing voice profiles based on speech samples, where a voice profile is determined and personalized on a computing device, and an authorization profile is used to securely provide the voice profile to associated users' devices via a cloud-based computing system.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If TTS templates are stored on a server for cloud access, then users can access text-to-speech functionality remotely, but the templates cannot be easily shared with multiple recipients for further usage

Engineering Contradiction:
Improveaccessibility of voice profilesVSAvoidshareability of voice profiles
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system segments the voice profile data into individual files stored on the server, each associated with specific authorization metadata. This allows the server to distribute different segments (voice profiles) to different authorized users independently, enabling both remote access and selective sharing capabilities simultaneously.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The server acts as an intermediary between the original voice profile creator and multiple recipients. It manages the authorization profiles, controls distribution, and facilitates sharing by mediating access rights. This intermediary role resolves the contradiction by enabling sharing functionality while maintaining centralized control and proper authorization management.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If voice profiles are personalized through speech model adaptation, then the voice output becomes more natural and user-specific, but the complexity of generating and managing these profiles increases

Engineering Contradiction:
Improvequality of voice synthesisVSAvoidcomplexity of voice profile management
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-adapting speech models to create personalized voice profiles before distribution. Speech samples are collected and processed in advance to generate adapted voice profiles that are then stored on the server. This preliminary processing reduces runtime complexity and enables high-quality personalized voice synthesis without requiring complex real-time adaptation during actual use.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates copies of adapted voice profiles from the original speech samples and stores them on the server for distribution to multiple authorized users. Instead of performing complex speech model adaptation every time a user needs a personalized voice, the system prepares and distributes pre-adapted voice profile copies, significantly reducing computational complexity while maintaining high synthesis quality.

Inventive Principle:
Principle #26Copying

3Reliability

If authorization profiles are implemented to control access, then security and proper user permissions are ensured, but the system requires additional processing and data management overhead

Engineering Contradiction:
Improveaccess control securityVSAvoidcomplexity of authorization management
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system merges the authorization profile data with the voice profile data in the server's database structure. By combining authorization metadata with voice profile information in a unified data model, the system reduces the overhead of managing separate authorization systems. This integration allows the server to handle access control efficiently without requiring complex separate authorization management infrastructure.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3428916B1Methods and systems for sharing of adapted voice profiles
Publication Date: 2021.12.22 GOOGLE LLC
  • EP3428916B1 patent drawingFigure 1
  • EP3428916B1 patent drawingFigure 2
  • EP3428916B1 patent drawingFigure 3

AI summary

Methods and systems for sharing of adapted voice profiles are provided. The method may comprise receiving, at a computing system, one or more speech samples, and the one or more speech samples may include a plurality of spoken utterances. The method may further comprise determining, at the computing system, a voice profile associated with a speaker of the plurality of spoken utterances, and including an adapted voice of the speaker. Still further, the method may comprise receiving, at the computing system, an authorization profile associated with the determined voice profile, and the authorization profile may include one or more user identifiers associated with one or more respective users. Yet still further, the method may comprise the computing system providing the voice profile to at least one computing device associated with the one or more respective users, based at least in part on the authorization profile.