Fine-Grained Textual Knowledge Transfer to Improve RNN Transducers for Speech Recognition and Understanding.
Vishal SunderSamuel ThomasHong-Kwang Jeff KuoBrian KingsburyEric Fosler-LussierPublished in: ICASSP (2023)
Keyphrases
- fine grained
- speech recognition
- knowledge transfer
- coarse grained
- hidden markov models
- language model
- automatic speech recognition
- speech synthesis
- knowledge sharing
- speech signal
- speaker identification
- pattern recognition
- access control
- speech recognizer
- transfer learning
- speech recognition technology
- speech recognition systems
- speaker independent
- artificial intelligence
- maximum likelihood
- markov random field
- software engineering
- nearest neighbor
- keywords
- image processing
- e learning