Simultaneous Speech Detection Based on MFCC-DTW with Two-Stage Normalization.
Radu-Sebastian MarinescuAlexandru George RusuCorneliu BurileanuDumitru BicaPublished in: TSP (2018)
Keyphrases
- speech recognition
- speech signal
- speaker identification
- detection accuracy
- dynamic time warping
- speaker recognition
- feature extraction
- automatic detection
- voice activity detection
- audio visual
- false alarms
- detection rate
- detection method
- automatic speech recognition
- dialogue system
- noisy environments
- preprocessing
- false positives
- anomaly detection
- distance measure
- language model
- probabilistic model
- feature selection
- acoustic features
- information retrieval