Innovative Multimodal Research

Building advanced speech datasets with emotional and prosodic insights for diverse languages.

A computer screen displaying a webpage about ChatGPT, focusing on optimizing language models for dialogue. The webpage has text describing the model and includes the OpenAI logo. The background is green with some purple graphical elements on the side.
A computer screen displaying a webpage about ChatGPT, focusing on optimizing language models for dialogue. The webpage has text describing the model and includes the OpenAI logo. The background is green with some purple graphical elements on the side.

Innovative Multimodal Research Solutions

We specialize in constructing multimodal datasets, integrating speech data, physiological signals, and advanced synthesis frameworks to enhance linguistic research and emotional analysis across diverse languages.

A collection of eggs features hand-drawn expressive faces, each displaying different emotions. The eggs are arranged closely together in an egg carton. One egg is brown with a sad face, while the others are white with happy, angry, or surprised expressions.
A collection of eggs features hand-drawn expressive faces, each displaying different emotions. The eggs are arranged closely together in an egg carton. One egg is brown with a sad face, while the others are white with happy, angry, or surprised expressions.

150+

15

Trusted by Experts

Proven Results

Innovative Speech Solutions

We specialize in multimodal dataset construction and hierarchical synthesis for advanced speech research applications.

Multimodal Dataset

Collect and annotate multilingual speech data with synchronized videos and physiological signals for research.

A display screen shows information about ChatGPT, a language model for dialogue optimization. The text includes details on how the model is used in conversational contexts. The background is primarily green, with pink and purple graphic lines on the right side. The OpenAI logo is positioned at the top left.
A display screen shows information about ChatGPT, a language model for dialogue optimization. The text includes details on how the model is used in conversational contexts. The background is primarily green, with pink and purple graphic lines on the right side. The OpenAI logo is positioned at the top left.
Hierarchical Synthesis

Utilize advanced frameworks to convert text into phonemes and enhance with dialect-specific rules effectively.

Optimize lightweight models for edge deployment on Raspberry Pi, ensuring efficiency and performance in applications.

Edge Deployment
A smartphone displays a black and white laughing emoji with tears of joy on its screen. The phone lies on a textured dark surface, creating a contrast between the screen's brightness and the background.
A smartphone displays a black and white laughing emoji with tears of joy on its screen. The phone lies on a textured dark surface, creating a contrast between the screen's brightness and the background.
A robotic face crafted from various mechanical and electronic components, including speakers, wires, and metal parts, arranged in a way to resemble facial features.
A robotic face crafted from various mechanical and electronic components, including speakers, wires, and metal parts, arranged in a way to resemble facial features.

Speech Research

Innovative multimodal dataset construction for speech analysis.

A young boy with short dark hair is opening his mouth wide, possibly screaming or shouting. The lighting is subdued, with a dark background that contrasts with his lighter skin tone. His expression conveys strong emotion, possibly excitement or frustration.
A young boy with short dark hair is opening his mouth wide, possibly screaming or shouting. The lighting is subdued, with a dark background that contrasts with his lighter skin tone. His expression conveys strong emotion, possibly excitement or frustration.
Phoneme Annotation

Multilevel labels for phoneme and emotion intensity.

A smiley face emoticon is seen hanging from a string, with a blurred background that has warm, golden tones. The emoticon has large, expressive eyes and an open mouth with a tongue sticking out.
A smiley face emoticon is seen hanging from a string, with a blurred background that has warm, golden tones. The emoticon has large, expressive eyes and an open mouth with a tongue sticking out.
Synthesis Framework

Hierarchical framework for phonetic and dialect enhancement.

Graffiti art featuring a large yellow emoticon wearing a white face mask, painted on a gray wall. There are various colorful tags and writings in purple, red, and orange, including a large hash symbol and the word 'SATO' above the emoticon. Additionally, a speech bubble with text is located on the left side.
Graffiti art featuring a large yellow emoticon wearing a white face mask, painted on a gray wall. There are various colorful tags and writings in purple, red, and orange, including a large hash symbol and the word 'SATO' above the emoticon. Additionally, a speech bubble with text is located on the left side.
A person with long dark hair appears to be excited or surprised, with wide open eyes and mouth. The facial expression suggests a strong emotion. The background is plain and light-colored.
A person with long dark hair appears to be excited or surprised, with wide open eyes and mouth. The facial expression suggests a strong emotion. The background is plain and light-colored.
Edge Deployment

Optimized models for lightweight edge computing solutions.

Ethical Validation

Collaborative efforts for ethical research practices.

Research

Innovative multilingual speech data collection and synthesis.

© 2025. All rights reserved.