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