TEVR: Improving Speech Recognition by Token Entropy Variance Reduction.
Hajo Nils KrabbenhöftErhardt BarthPublished in: CoRR (2022)
Keyphrases
- speech recognition
- variance reduction
- language model
- sample size
- monte carlo
- hidden markov models
- speech recognizer
- pattern recognition
- speech processing
- speech signal
- speaker identification
- speech synthesis
- speech recognition technology
- automatic speech recognition
- noisy environments
- speaker independent
- speaker dependent
- importance sampling
- confidence intervals
- neural network
- speech recognition systems
- training data