Multimodal and Multiresolution Speech Recognition with Transformers.
Georgios ParaskevopoulosSrinivas ParthasarathyAparna KhareShiva SundaramPublished in: ACL (2020)
Keyphrases
- speech recognition
- multiresolution
- hidden markov models
- language model
- speech recognizer
- multi modal
- automatic speech recognition
- speech signal
- speech processing
- speech synthesis
- speech recognition technology
- noisy environments
- quadtree
- speech recognition systems
- wavelet transform
- pattern recognition
- image fusion
- speech understanding
- speaker identification
- subband
- audio visual speech recognition
- discrete wavelet transform
- speaker diarization
- wavelet coefficients
- speaker independent
- cepstral coefficients
- speech recognition errors
- speech retrieval
- image processing
- speech recognizers
- isolated word
- information retrieval