FPGA Implementation of a Configurable Vocal Feature Extraction Embedded System for Dysarthric Speech Recognition.
Iacopo CasaliniMarco MariniLuca FanucciPublished in: ApplePies (2021)
Keyphrases
- speech recognition
- fpga implementation
- speech signal
- feature extraction
- cepstral coefficients
- hardware implementation
- speaker identification
- pattern recognition
- automatic speech recognition
- speech synthesis
- language model
- hidden markov models
- noisy environments
- speech processing
- speech recognition systems
- extracted features
- speech recognizer
- image processing
- frequency domain
- mel frequency cepstral coefficients
- signal processing
- speech retrieval
- speech recognition technology
- efficient implementation
- field programmable gate array
- background noise
- feature selection
- image processing algorithms
- principal component analysis
- acoustic features
- extracting features
- feature vectors
- feature space
- face recognition
- isolated word
- speaker recognition
- transfer function
- speaker independent
- artificial intelligence
- speech recognizers