Temporal Early Exiting for Streaming Speech Commands Recognition.
Raphael TangKarun KumarJi XinPiyush VyasWenyan LiGefei YangYajie MaoG. Craig MurrayJimmy LinPublished in: ICASSP (2022)
Keyphrases
- recognition engine
- speech recognition
- recognition rate
- pattern recognition
- object recognition
- automatic speech recognition systems
- spatio temporal
- recognition accuracy
- real time
- continuous speech recognition
- temporal information
- spoken words
- speech corpus
- speech recognition systems
- recognition process
- feature extraction
- automatic recognition
- speech sounds
- temporal constraints
- video streaming
- text recognition
- gesture recognition
- spatial and temporal
- space time
- automatic speech recognition
- audio visual
- noisy environments
- spoken language
- speaker independent
- temporal reasoning
- activity recognition
- hidden markov models