Voice Plugins for i.MX Applications Processors

This demo covers advanced voice processing technologies, highlighting features such as voice detection, voice command recognition, AI noise reduction (AI-NR), echo cancellation and speech-to-text transcription. In this video, you will be introduced to how these capabilities—powered by AI models—can be integrated into devices for real-time, local audio processing through GStreamer. These innovations are designed to enhance communication quality and enable customizable voice-driven applications.

Explore NXP's voice processing solutions for consumer and industrial applications.

Key Highlights

Watch real-time voice command recognition and customizable command lists using the voice intelligent technology (VIT) engine
See voice activity detection (VAD) and direction of arrival (DOA) using two microphones
Catch a demonstration of advanced AI-driven noise reduction and echo cancellation technologies, featuring significant enhancements in audio clarity for both playback and recording scenarios
Become familiar with on-device speech-to-text transcription using an optimized Whisper model, with results displayed directly over the video

Resources

展开收起