On time-frequency masking in voiced speech.
Jan SkoglundW. Bastiaan KleijnPublished in: IEEE Trans. Speech Audio Process. (2000)
Keyphrases
- speech signal
- speech processing
- signal processing
- emotion recognition
- speech recognition
- automatic speech recognition
- vocal tract
- speech segments
- audio visual
- speech synthesis
- linear prediction
- human visual system
- noisy environments
- hidden markov models
- pattern recognition
- emotional speech
- speaker identification
- signal analysis
- frequency domain
- non stationary
- empirically derived
- recognition engine
- speech recognizer
- endpoint detection
- automatic speech recognition systems
- speaker recognition
- multi modal
- machine learning
- broadcast news
- audio features
- short time fourier transform
- image processing
- artificial intelligence
- neural network