Emotional Content Comparison in Speech Signal Using Feature Embedding.
Stefano RovettaZied MnasriFrancesco MasulliPublished in: IIH-MSP (1) (2017)
Keyphrases
- speech signal
- speech recognition
- cepstral coefficients
- speaker identification
- non stationary
- automatic speech recognition
- noisy environments
- multimedia
- vocal tract
- linear prediction
- hidden markov models
- background noise
- speaker recognition
- feature set
- spectral analysis
- acoustic features
- speech quality
- hearing aids
- neural network
- automatic speech recognition systems