Two-stage speech/music classifier with decision smoothing and sharpening in the EVS codec.
Vladimir MalenovskyTommy VaillancourtWang ZheKihyun ChooVenkatraman AttiPublished in: ICASSP (2015)
Keyphrases
- step size
- electric vehicles
- audio signals
- speech music discrimination
- speech recognition
- feature selection
- decision making
- audio features
- speech signal
- feature set
- edge detection
- feature space
- audio recordings
- music information retrieval
- audio visual
- multiresolution
- multiscale
- video coding
- real time
- fuzzy logic
- cost function
- edge preserving smoothing
- information systems