Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition.
Maarten Van SegbroeckSri Harish MallidiBrian KingI-Fan ChenGurpreet ChadhaRoland MaasPublished in: CoRR (2020)
Keyphrases
- multi view
- automatic speech recognition
- speech recognition
- single view
- hidden markov models
- d objects
- multiple views
- depth map
- speech signal
- broadcast news
- conversational speech
- three dimensional
- view synthesis
- speech retrieval
- semi supervised
- range images
- multi view face detection
- multi view clustering
- multiple viewpoints
- multi view images
- multi view reconstruction
- co training
- speech sounds
- neural network
- surface reconstruction
- question answering
- pattern recognition
- face recognition
- image sequences
- feature selection
- computer vision