ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition.
Martin RadfarRohit BarnwalRupak Vignesh SwaminathanFeng-Ju ChangGrant P. StrimelNathan SusanjAthanasios MouchtarisPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- recurrent neural networks
- hidden markov models
- neural network
- language model
- recurrent networks
- complex valued
- reservoir computing
- echo state networks
- speech synthesis
- feed forward
- hidden layer
- speech signal
- automatic speech recognition
- speech recognition systems
- speech recognizer
- speech processing
- deep learning
- speech understanding
- keyword spotting
- speech recognition technology
- speaker identification
- pattern recognition
- artificial neural networks
- speaker dependent
- speech recognizers
- fuzzy logic
- speaker independent
- acoustic models
- bayesian networks