A Low Power DNN-based Speech Recognition Processor with Precision Recoverable Approximate Computing.
Bo LiuXuetao WangRenyuan ZhangAnfeng XueZiyu WangHaige WuHao CaiPublished in: ISCAS (2022)
Keyphrases
- speech recognition
- low power
- high speed
- single chip
- gate array
- low cost
- power consumption
- hidden markov models
- language model
- automatic speech recognition
- speech recognizer
- speech processing
- speech signal
- pattern recognition
- speech recognition technology
- speech recognition systems
- logic circuits
- image sensor
- speech synthesis
- low power consumption
- speaker identification
- cmos technology
- power reduction
- speaker adaptation
- speech recognizers