Joint Training End-to-End Speech Recognition Systems with Speaker Attributes.
Sheng LiXugang LuRaj DabrePeng ShenHisashi KawaiPublished in: Odyssey (2020)
Keyphrases
- end to end
- speech recognition
- speech recognition systems
- speech recognizer
- congestion control
- training set
- hidden markov models
- speaker independent
- automatic speech recognition
- language model
- pattern recognition
- speaker identification
- information retrieval
- model selection
- speech signal
- admission control
- image processing
- feature selection
- neural network