On Exploring Audio Anomaly in Speech.
Tiago RoxoJoana Cabral CostaPedro R. M. InácioHugo ProençaPublished in: WIFS (2023)
Keyphrases
- audio stream
- audio visual
- broadcast news
- audio signals
- text to speech
- speaker identification
- cepstral features
- emotion recognition
- anomaly detection
- audio recordings
- audio features
- prosodic features
- speech recognition
- digital audio
- speech music discrimination
- linear predictive coding
- speech processing
- audio video
- multi modal
- multi stream
- automatic transcription
- spoken documents
- human language
- multimedia
- acoustic signals
- speech signal
- acoustic features
- automatic speech recognition
- speech synthesis
- speaker diarization
- intrusion detection
- video streams
- signal processing
- speaker verification
- visual information
- detecting anomalies
- speaker recognition
- abnormal events
- speech recognition technology
- spoken language
- content based video retrieval
- mel frequency cepstral coefficients
- facial expressions
- acoustic signal
- low level
- network traffic
- endpoint detection
- pattern recognition
- digital video