Extending RNN-T-based speech recognition systems with emotion and language classification.
Zvi KonsHagai AronowitzEdmilson da Silva MoraisMatheus DamascenoHong-Kwang KuoSamuel ThomasGeorge SaonPublished in: CoRR (2022)
Keyphrases
- pattern recognition
- image classification
- speech recognition systems
- speech recognition
- classification accuracy
- feature extraction
- feature vectors
- neural network
- support vector
- text classification
- machine learning
- image retrieval
- natural language
- feature selection
- high dimensional
- nearest neighbor
- information retrieval systems
- feature space
- training data