Hybrid DNN-Latent structured SVM acoustic models for continuous speech recognition.
Suman V. RavuriPublished in: ASRU (2015)
Keyphrases
- continuous speech recognition
- training process
- support vector machine svm
- support vector
- acoustic models
- support vector machine
- knn
- training data
- kernel function
- feature extraction
- feature selection
- feature space
- discriminative training
- training set
- feature vectors
- machine learning
- kernel methods
- broadcast news
- digit recognition
- image processing