This page partially uses JavaScript. This page may not operate normally when these functions are not supported by your browser or the setting is disabled.

Toshiba AI Technology Catalog

Speech dialogue
Media transformation
Media generation

RECAIUS™ Text-To-Speech middleware using DNN technology

Text-To-Speech middleware using DNN (Deep Neural Network) technology for general purpose CPU processors.

To develop Text-To-Speech middleware achieving highly improved voice sound quality.
Works on general purpose CPU processors by reducing calculation costs and memory footprint.

Zoom Image

Applications

For reading text information
For talkback function and speech guidance
For reproduction of the characteristics of voice actors and character voices

Benchmarks, strengths, and track record

Works on the user’s local devices with smooth and natural voice quality
Smaller memory footprint compared with conventional TTS middleware

Inquiries

RECAIUS inquiry site (In Japanese)

Please include the title “Toshiba AI Technology Catalog: RECAIUS™ Text-To-Speech middleware using DNN technology” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.

References:

TAMURA Masatsune et.al.: “Next-generation Speech Synthesis Technology based on Deep Learning with High-fidelity Human-like Speech and ToSpeak Functionality,” (PDF)(384KB) Toshiba review Vol.78, No.5, pp.45-49 (2023).
YAGUCHI Atsushi et.al.: “DNN Compaction Method Eliminating Zero Weight Coefficients,” (PDF)(671KB) Toshiba review Vol.74, No.4, pp.42-45 (2019).

Return to “Toshiba AI Technology Catalog” page