AUDIO INTELLIGENCE TECHNOLOGY

Detect, extract, and recognize sound intelligently using audio sensing, signal processing and acoustic analytics technologies

Sound/Speech Recognition

Monitor, capture, and analyze sound/speech

Environment Sound Recognition

  • Applying deep neural networks to recognize scream, gun shot, glass-breaking, etc. for security event detection

  • Auto tagging for video/audio contents

Multimodal Emotion Recognition

  • Feature extraction & classification to determine a speaker’s emotion: angry, happy or sad, etc.

Simultaneous Multi-speaker Recognition

  • Using beamforming and speech direction estimation technology for simultaneous speech recognition of multiple speakers

Natural Language Processing

  • Developing technology for the processing of semantics, sentiments, and meanings of written and spoken languages

Audio Pre-Processing

Noise Reduction

  • Remarkable noise reduction for speech/voice recognition enhancement

Sound Source Separation

  • Sound source localization and separation based on microphone array technologies

Personal Audio Space

  • Improving sound quality and directivity of parametric directional speakers