Multiresolution and Multimodal Speech Recognition with Transformers.
Georgios ParaskevopoulosSrinivas ParthasarathyAparna KhareShiva SundaramPublished in: CoRR (2020)
Keyphrases
- speech recognition
- multiresolution
- hidden markov models
- language model
- speech processing
- audio visual speech recognition
- automatic speech recognition
- wavelet transform
- multi stream
- pattern recognition
- speech signal
- multi modal
- speech recognition technology
- speech recognition systems
- speech synthesis
- quadtree
- speech recognizer
- audio visual
- speaker identification
- wavelet coefficients
- image fusion
- speaker dependent
- speech recognizers
- noisy environments
- speech understanding
- speaker independent
- subband
- image processing
- multimedia
- discrete wavelet transform
- n gram