Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors.
Yajie MiaoHao ZhangFlorian MetzePublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2015)
Keyphrases
- acoustic models
- speech recognition
- neural network
- training process
- hidden markov models
- automatic speech recognition
- speech recognizer
- discriminative training
- broadcast news
- pattern recognition
- speaker independent
- training data
- back propagation
- feature vectors
- language model
- spoken language
- input pattern
- speech signal
- image processing
- audio visual
- probabilistic interpretation
- feature extraction
- non stationary
- computer vision