On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode.
Raviraj JoshiSubodh KumarPublished in: CoRR (2022)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- automatic speech recognition
- language model
- pattern recognition
- speech signal
- speech processing
- speech recognizer
- speech synthesis
- speaker identification
- speech retrieval
- speech recognition technology
- noisy environments
- congestion control
- speech recognition systems
- isolated word
- speaker independent
- speech recognizers
- audio visual speech recognition
- error propagation
- neural network
- computer vision
- speaker dependent
- vector quantization
- maximum likelihood
- wavelet transform