Artificial Intelligence Audio



Artificial Intelligence Audio (AIA) Engine provides the function to convert audio signals into an output that sounds as if it is coming from a specific direction or in a virtual space.

If you listen to mono audio signals with earphones or headphones, it is difficult to feel a sense of direction or space. AIA Engine lets the user convert mono signals into stereo signals that have directional, distance, and spatial effects to enjoy realistic sounds with earphones or headphones.


AIA Engine provided by ThinQ.AI has the following features:

SSP 엔진의 특징
Features Description
Directional effect

Converts audio signals to deliver a sound effect where the output sounds as if it is coming from specific directions on earphones or headphones.


The user can set up to eight different directions as shown in the figure below.


Distance effect

Converts audio signals to remove the uncomfortable sound that feels like it lingers inside the head and make the sound feel more external and natural on earphones or headphones.


Spatial effect

Converts audio signals using spatial acoustic modeling technology to make the output sound feel more realistic and as if the listener is inside a certain virtual space.
Users can download an audio file that can realistically express the characteristics of a virtual space (concert hall, gym, forest, cave, etc.) and apply it to the output.



Engine Structure

AIA Engine receives audio data as input values, and generates and outputs audio data applied with the set effects.


Example of Use

AIA Engine can be used in various fields where audio data is used. For example, using audio data with AIA Engine applied when providing a home training service can make the service more lively.


Application of directional/distance effects

AIA Engine can be used to apply directional and distance effects to audio data for the guide voice of a home trainer to help the user better understand directions and positions while training.


Application of spatial effect

Sound effects can be applied to the trainer’s guide voice that fits a specific virtual space to provide a more realistic experience to the user training in a virtual space.