ThinQ.AI provides various AI functions. For the details of each function, please refer to the following:
Speech & Language
Speech Signal Processing
This function removes the noise from digitized speech signals. This is an essential function for the pre-processing of recognized speeches.
Target Speech Enhancement
This function removes the noise from the voice signals converted to digital signals. This engine is an essential function for the preprocessing to process voice signals of In-Vehicle Infotainment.
Multi-device Wakeup Arbitration
This function selects the most suitable device for a user when multiple devices recognize the same trigger word at the same time.
Hybrid Trigger Word Detection
This function detects whether there is a specific trigger word in a user's speech input from the microphone. You can increase the accuracy by sending the result to the server.
Automatic Speech Recognition
This function processes a user's speed signal input from the microphone and then converts it into a text.
Natural Language Processing
This function converts the natural language, which is the human language, into the structured language that can be understood by the machine to grasp the meaning of sentences and figure out the user's intention.
Text to Speech
This function converts text data into speech signals.
Emotion Text to Speech
This function converts text and emotional data into speech signals.
This function recognizes a user's emotion through facial expression, voice and text.
Vision Pack - Food Detection
The function detects products like commercial food products, fruits, and vegetables stored in a refrigerator.
Driver State Monitoring
This engine detects a user's face, tracks their gaze, and determines whether their eyes are closed or blinking.
The gesture recognition function detects a person's hands from an input video and recognizes the posture and motion of the hands.
This function detects a person's face from an input video or an image data to figure out the number of persons and the position and size of the faces.
This function detects a person's face from an input video or image data, and then finds the information on the desired person in the database.
Age Gender Recognition
This function detects a person's face from an input video or an image data and guesses the age/gender of the person.
This complex authentication function authenticates users conveniently and enhances security by using a variety of biometrics means in combination.
The sleep state measurement function detects snoring and interruption of breathing in the data measured during sleep, and then analyzes sleep patterns and phases.
Automatic Data Preprocessing & Analysis Toolkit
This toolkit facilitates data preprocessing, learning, and analysis in an intuitive and user-friendly way.
Cloud Deep Learning Toolkit
This web service helps developers to train an AI engine through deep learning by configuring data that suits their purposes.
Embedded Deep Neural Network
This provides a deep learning model optimization function so that a deep learning model developed in the PC can operate in the embedded environment.
Emotion Recognition Monitoring Toolkit
This toolkit analyze and monitor the causes of the ER (Emotion Recognition) Engine's results.
Feedback Analysis System
This data analysis tool improves the performance of a trained machine learning model in an actual user environment.
Platform Development Kit
This tool generates the basic codes automatically so that a user can develop the ThinQ.AI SDK easily.
SSP Engine Tuning Tool
This tool helps developers effectively use SSP Engine by tuning parameters related to voice signals in various noise environments.
ThinQ.AI Performance Checker
This tool helps a user recognizes speech recognition and measures the performance of your voice recognition function and engine performance of differences in domain and environment.
Voice Agent Development Tool
This web service is a web-based development tool for the development of a voice chat agent.
Open Innovation Technology
Open Innovation Technology
This is a service that combines the technologies of ThinQ.AI with those of partners. ThinQ.AI helps developers produce new products using OI technologies.
VisionLabs works with ThinQ.AI to provide face recognition and detection in images.
Sensory is a company that develops technologies for speech recognition, trigger word recognition, natural language processing, face and voice biometrics, and computer vision.
AI SoC: LG8111
The LG8111 AI SoC is a semiconductor chip that supports artificial intelligence functions. This has a built-in 'LG Neural Engine', an artificial intelligence processor that mimics the human's brain neural network.
This is the specification of the ThinQ.AI SDK and Cloud API.
The hardware support and performance required for each engine varies by OS. Therefore, there may be a difference in engines and performance supported by OS.
|Speech & Language||Hybrid Trigger Word Detection (HTWD)||○||○||○||○||○|
|Automatic Speech Recognition (ASR)||○||○||○||○||○|
|Natural Language Processing (NLP)||○||○||○||○||○|
|Text to Speech (TTS)||○||○||○||○||○|
|Speech Signal Processing (SSP)||○||○||○||X||X|
|Target Speech Enhancement (TSE)||○||○||X||X||X|
|Multi-device Wakeup Arbitration (MWA)||○||○||○||X||○|
|Emotion Text to Speech (ETTS)||X||X||○||X||○|
|Emotion||Emotion Recognition (ER)||○||○||○||X||○|
|Vision||Face Detection (FD)||○||○||○||X||X|
|Face Recognition (FR)||○||○||○||X||X|
|Hand Gesture (HG)||○||○||○||X||X|
|Age Gender Recognition (AGR)||○||○||○||X||X|
|Driver State Monitoring (DSM)||○||X||○||X||X|
|Vision Pack - Food Detection (VPF)||X||X||X||X||○|
|Biometrics||Multi-modal Biometrics (MMB)||○||○||X||X||X|
|Sleep Detection (SD)||○||○||X||X||X|