Efficient Speech Detection in Environmental Audio Using Acoustic Recognition and Knowledge Distillation.
Drew PriebeBurooj GhaniDan StowellPublished in: Sensors (2024)
Keyphrases
- environmental sounds
- audio visual
- speech sounds
- visual speech
- acoustic features
- speaker identification
- speaker independent
- recognition engine
- noisy environments
- speech recognition
- multimedia
- audio stream
- speech recognition systems
- domain knowledge
- recognition rate
- feature extraction
- audio signals
- multi modal
- knowledge base
- automatic transcription
- voice activity detection
- visual information
- knowledge management
- mel frequency cepstral coefficients
- object detection
- emotion recognition
- pattern recognition
- prosodic features
- digital audio
- object recognition
- text recognition
- speech processing
- audio signal
- audio features
- detection method
- cepstral features
- speaker verification
- speech signal
- action recognition
- character recognition