Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning.
Brian TestaYi XiaoAvery GumpAsif SalekinPublished in: CoRR (2022)
Keyphrases
- real time
- machine learning
- emotional speech
- emotion recognition
- speech recognition
- face detection and tracking
- detection algorithm
- text to speech synthesis
- low cost
- emotional state
- speech processing
- pattern recognition
- voice activity detection
- detection method
- acoustic features
- false positives
- object detection
- learning algorithm
- noisy environments
- emotion classification
- acoustic signal
- personal information
- machine learning methods
- privacy preserving
- speech sounds
- formant frequencies
- detecting and tracking multiple
- speaker independent
- speech recognition systems
- mel frequency cepstral coefficients
- dialogue system
- automatic speech recognition
- security issues
- speech signal
- anomaly detection
- natural language processing
- facial expressions
- control system
- decision trees