FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks.
Minjae LeeKyuyeon HwangJinhwan ParkSungwook ChoiSungho ShinWonyong SungPublished in: SiPS (2016)
Keyphrases
- speech recognition
- low power
- recurrent neural networks
- low cost
- power consumption
- high speed
- neural network
- language model
- hidden markov models
- feed forward
- speech processing
- recurrent networks
- automatic speech recognition
- echo state networks
- application specific
- pattern recognition
- speech recognizer
- speech signal
- low power consumption
- artificial neural networks
- noisy environments
- speaker identification
- embedded systems
- speech synthesis
- isolated word
- speech recognition technology
- logic circuits
- field programmable gate array
- image processing
- speaker dependent
- bayesian networks
- gate array
- mixed signal
- real time
- hardware implementation
- machine vision