Investigates various Speech signal processing schemes for acoustic modeling so that more robust speech recognition can be achieved. Our aim is to perform the state-of-art research providing effective means for achieving:
Context Awareness System based on Acoustic & Visual
Admin 2021-04-08 👁️ 498
Context Awareness System based on Acoustic & Visual
Contents
2. Main algorithm and principle
1. Introduction
This is the context awareness system based on acoustic and visual data in mobile platform. By analyzing the acoustic and visual source from the microphone and camera of the smart-phone (mobile device), we can get some cues for context. The Environments we can recognize are followings:
- 10 Acoustic environments
- 4 visual environments
Indoor
Outdoor
Outdoor
Moving Detection
2. Main algorithm and principle
- Acoustic
1. Noisy environments detection using the average value of log sound energy
2. MFCC feature extraction for context awareness
3. GMM(Gaussian Mixture Model) for the classification
- Visual
1. Low intensity : using the image intensity, light detector
2. Face: skin region detector
3. Indoor/Outdoor : Nearest neighbor classifier using color/texture features
4. Moving detection : Neural network classifier using the optical flow for feature
- high speed in mobile platform for real-time
1. Dynamic mixture GMM for acoustic modeling
2. Recognition process scheduling
- System Architecture
3. Application or Demo