Mixtures of Deep Neural Experts for Automated Speech Scoring.
Sara PapiEdmondo TrentinRoberto GretterMarco MatassoniDaniele FalavignaPublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- semi automated
- mixture model
- network architecture
- fully automated
- neural network
- automatic speech recognition
- audio visual
- dialogue system
- spoken language
- heavy tailed
- spontaneous speech
- mixtures of gaussians
- associative memory
- domain experts
- domain knowledge
- data sets
- deep learning
- biologically plausible
- scoring model