A Comparison of Formant and CNN Models for Vowel Frame Recognition.
Ondrej SuchSantiago BarredaAnton MojsejPublished in: ITAT (2019)
Keyphrases
- object recognition
- recognition rate
- pattern recognition
- probabilistic model
- neural network
- artificial neural networks
- prior knowledge
- object models
- recognition accuracy
- experimental data
- statistical models
- vocal tract
- data sets
- automatic recognition
- video frames
- complex systems
- parameter estimation
- model selection
- feature extraction