17959050. SPEECH SYNTHESIS DEVICE AND SPEECH SYNTHESIS METHOD simplified abstract (LG ELECTRONICS INC.)

SPEECH SYNTHESIS DEVICE AND SPEECH SYNTHESIS METHOD

Organization Name

LG ELECTRONICS INC.

Inventor(s)

Sangki Kim of Seoul (KR)

Sungmin Han of Seoul (KR)

Siyoung Yang of Seoul (KR)

SPEECH SYNTHESIS DEVICE AND SPEECH SYNTHESIS METHOD - A simplified explanation of the abstract

This abstract first appeared for US patent application 17959050 titled 'SPEECH SYNTHESIS DEVICE AND SPEECH SYNTHESIS METHOD

Simplified Explanation

The patent application describes a speech synthesis device that can generate a synthetic voice with different speech styles. It includes a speaker and a processor that acquires voice feature information from a text and user input. The device uses a decoder trained to minimize the difference between feature information of a learning text and characteristic information of a learning voice to generate the synthetic voice, which is then output through the speaker.

• The device can generate a synthetic voice with various speech styles.
• It acquires voice feature information from a text and user input.
• The synthetic voice is generated using a decoder trained to minimize the difference between feature information of a learning text and characteristic information of a learning voice.
• The generated synthetic voice is output through a speaker.

Potential Applications

• Assistive technology for individuals with speech impairments.
• Voiceover services for media production.
• Virtual assistants and chatbots with customizable speech styles.
• Language learning tools with different accents and intonations.

Problems Solved

• Limited availability of speech synthesis devices with customizable speech styles.
• Difficulty in generating synthetic voices that accurately mimic specific speech characteristics.
• Lack of flexibility in adjusting speech styles in existing speech synthesis technology.

Benefits

• Provides a wide range of speech styles for synthetic voices.
• Allows users to customize the speech style according to their preferences.
• Enhances the naturalness and expressiveness of synthetic voices.
• Enables more realistic and personalized interactions with speech synthesis technology.

Original Abstract Submitted

Provided is a speech synthetic device capable of outputting a synthetic voice having various speech styles. The speech synthesis device includes a speaker, and a processor to acquire voice feature information through a text and a user input; generate a synthetic voice, by receiving the text and the voice feature information inputs into a decoder supervised-trained to minimize a difference between feature information of a learning text and characteristic information of a learning voice, and output the generated synthetic voice through the speaker.