Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution.
Yangyang ShiChunyang WuDilin WangAlex XiaoJay MahadeokarXiaohui ZhangChunxi LiuKe LiYuan ShangguanVarun NagarajaOzlem KalinliMike SeltzerPublished in: CoRR (2021)
Keyphrases
- speech recognition
- fuzzy logic
- speech signal
- data streams
- causal relationships
- broadcast news
- text to speech
- fault diagnosis
- real time
- video streaming
- streaming data
- image processing
- recognition engine
- power transformers
- speech synthesis
- spoken language
- causal networks
- automatic speech recognition
- audio visual
- power system
- endpoint detection
- dialogue system
- causal theories
- real time streaming
- bayesian networks
- high voltage
- streaming media
- stream processing
- multimodal interfaces
- causal graph
- causal relations
- speaker identification
- causal reasoning
- causal models
- genetic algorithm