Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing.
Jun QiChao-Han Huck YangPin-Yu ChenJavier TejedorPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2023)
Keyphrases
- speech processing
- low rank
- trace norm
- neural network
- high order
- tensor decomposition
- signal processing
- speech recognition
- convex optimization
- linear combination
- missing data
- pattern recognition
- matrix factorization
- natural language processing
- multimedia systems
- low rank matrix
- matrix completion
- singular value decomposition
- speaker identification
- artificial intelligence
- semi supervised
- high dimensional data
- kernel matrix
- machine learning
- english text
- manifold learning
- riemannian manifolds
- pairwise
- computer vision
- diffusion tensor
- hidden markov models
- small number
- information retrieval
- markov random field
- clustering algorithm
- language model
- information retrieval systems