I3D: Transformer Architectures with Input-Dependent Dynamic Depth for Speech Recognition.
Yifan PengJaesong LeeShinji WatanabePublished in: ICASSP (2023)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech processing
- speech synthesis
- pattern recognition
- speech signal
- automatic speech recognition
- speech recognition technology
- noisy environments
- keyword spotting
- speech recognizer
- speech understanding
- speech recognizers
- speaker identification
- speech recognition systems
- speaker independent
- isolated word
- audio visual speech recognition
- information retrieval
- speech recognition errors
- multi modal
- image processing