Text-to-Voice Conversion Using User-Specific Voice Profiles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing communication technologies lack adaptability and flexibility in converting text information to audio, as they can only convert text to audio with specific voice characteristic parameters, limiting user experience.

Innovation Solution

A method and apparatus that obtain voice characteristic parameters from a second terminal based on identification information, allowing conversion of text information to audio with customizable voice characteristics, enhancing adaptability and flexibility.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If text information is converted to audio with fixed voice characteristic parameters, then the conversion process is simple, but the adaptability and flexibility of conversion are poor

Engineering Contradiction:
Improveadaptability and flexibility of conversionVSAvoidcomplexity of conversion process
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-collecting and storing voice characteristic parameters (such as pitch, timbre, tone) of multiple users in a database before the text-to-voice conversion process. When a conversion request is received, the system retrieves the appropriate pre-stored parameters based on user identification, eliminating the need for real-time parameter analysis and significantly improving conversion flexibility without adding complex real-time processing

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces a database as an intermediary component that stores the mapping relationship between user identification information and voice characteristic parameters. This intermediary layer decouples the conversion process from the parameter selection process, allowing the system to maintain simple conversion logic while achieving high adaptability through the intermediary database lookup

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If text information is converted to audio with specific voice characteristic parameters, then the conversion process is straightforward, but the user experience is limited

Engineering Contradiction:
Improveease of conversion operationVSAvoiduser experience adaptability
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements self-service by enabling the system to automatically select appropriate voice characteristic parameters based on user identification information without requiring manual user input or configuration. The system autonomously queries the database using the user's ID and retrieves the corresponding voice parameters, making the conversion process both easy to operate and highly adaptable to different users

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent applies parameter changes by dynamically selecting different voice characteristic parameters (pitch, timbre, tone) based on the user's identification information. Instead of using fixed parameters, the system changes the parameters according to the retrieved user profile, thereby improving user experience while maintaining straightforward conversion operations

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS9343061B2Method and apparatus for converting text information
Publication Date: 2016.05.17 HUAWEI DEVICE CO LTD
  • US9343061B2 patent drawing
  • US9343061B2 patent drawing
  • US9343061B2 patent drawing

AI summary

The present invention provides a method and an apparatus for converting text information. The method includes: receiving, by a first terminal, a call or data from a second terminal; obtaining, by the first terminal, according to a mapping relationship between identification information of the second terminal and voice characteristic parameters of an user of the second terminal, the voice characteristic parameters of the user of the second terminal corresponding to the identification information of the second terminal when the first terminal is in a working mode of text-to-voice conversion; and converting, by the first terminal, related text information about the call or data to audio information with the voice characteristic parameters of the user of the second terminal.