Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation.
Keqi DengPhilip C. WoodlandPublished in: CoRR (2024)
Keyphrases
- speech recognition
- network architecture
- neural network
- multi label
- machine translation
- image labeling
- automatic speech recognition
- query translation
- speech signal
- cross language information retrieval
- text to speech
- recognition engine
- speech synthesis
- speaker recognition
- neural fuzzy
- spoken language
- emotion recognition
- speaker identification
- audio visual
- associative memory
- language model
- parallel corpora
- vocal tract
- audio stream
- neural model
- noisy environments
- dialogue system
- biologically inspired
- visual information
- text categorization
- multi modal
- markov random field
- clustering algorithm