Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition.
Belen AlastrueyLukas DrudeJahn HeymannSimon WieslerPublished in: CoRR (2023)
Keyphrases
- multi view
- automatic speech recognition
- speech recognition
- single view
- multiple views
- hidden markov models
- d objects
- speech signal
- conversational speech
- broadcast news
- depth map
- multi view clustering
- semi supervised
- view synthesis
- speech retrieval
- three dimensional
- co training
- multi view reconstruction
- surface reconstruction
- multi view stereo
- range images
- multi view learning
- unlabeled data
- labeled data
- visual hull
- pairwise
- free viewpoint
- neural network