Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System
ISWC '04 Proceedings of the Eighth International Symposium on Wearable Computers
Assistive intelligent environments for automatic health monitoring
Assistive intelligent environments for automatic health monitoring
Recognizing context for annotating a live life recording
Personal and Ubiquitous Computing - Memory and Sharing of Experiences
SoundSense: scalable sound sensing for people-centric applications on mobile phones
Proceedings of the 7th international conference on Mobile systems, applications, and services
Acoustic event detection in meeting-room environments
Pattern Recognition Letters
Robust Radio Broadcast Monitoring Using a Multi-Band Spectral Entropy Signature
CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Coherent bag-of audio words model for efficient large-scale video copy detection
Proceedings of the ACM International Conference on Image and Video Retrieval
A survey of mobile phone sensing
IEEE Communications Magazine
Accurate and privacy preserving cough sensing using a low-cost microphone
Proceedings of the 13th international conference on Ubiquitous computing
Passive and In-Situ assessment of mental and physical well-being using mobile sensors
Proceedings of the 13th international conference on Ubiquitous computing
| Hi-index | 0.00 |
Context identification is one of the key challenges in Ubicomp. An application example is providing contextual information to caregivers of person with dementia to identify assistance needs. Environmental audio provides significant and representative information of the context and the challenge is to automatically identify audio cues coming from overlapping sound sources without sophisticated microphone arrangements. My thesis proposes a succinct representation of the audio, based on the spectral entropy of the signal, and we show experimentally its robustness to source overlap and noise. This would permit ubiquitous applications that perform sound-based activity identification directly in mobile phones.