Pitch-based emphasis detection for segmenting speech recordings.
Barry AronsPublished in: ICSLP (1994)
Keyphrases
- audio visual
- acoustic features
- spontaneous speech
- speech recognition
- temporal segmentation
- detection algorithm
- automatic detection
- false alarms
- detection method
- noisy environments
- multi modal
- speech signal
- detection rate
- detection accuracy
- object detection
- voice activity detection
- false positives
- fundamental frequency
- formant frequencies
- audio recordings
- recognition engine
- text recognition
- video recordings
- automatic speech recognition