Energy-efficient MFCC extraction architecture in mixed-signal domain for automatic speech recognition.
Qin LiHuifeng ZhuFei QiaoQi WeiXinjun LiuHuazhong YangPublished in: NANOARCH (2018)
Keyphrases
- energy efficient
- automatic speech recognition
- speech recognition
- speech signal
- mixed signal
- wireless sensor networks
- energy consumption
- sensor networks
- low power
- multi channel
- hidden markov models
- multi core architecture
- acoustic features
- broadcast news
- base station
- energy efficiency
- conversational speech
- data transmission
- power consumption
- speech retrieval
- feature extraction
- noisy environments
- real time
- pattern recognition
- speaker identification
- routing protocol
- design considerations
- digital circuits
- cmos technology
- energy saving
- computer vision
- language model
- neural network