Automatic speaker verification from affective speech using Gaussian mixture model based estimation of neutral speech characteristics.
Anderson R. AvilaDouglas D. O'ShaughnessyTiago H. FalkPublished in: Speech Commun. (2021)
Keyphrases
- speaker verification
- speaker recognition
- emotion recognition
- noisy environments
- prosodic features
- audio visual
- speech recognition
- speech signal
- acoustic features
- gaussian mixture model
- automatic speech recognition
- speech synthesis
- pattern recognition
- text to speech
- affective states
- emotional state
- broadcast news
- speaker identification
- multilayer perceptron
- sentiment analysis
- face detection
- human computer interaction
- high dimensional
- neural network