A low latency modular-level deeply integrated MFCC feature extraction architecture for speech recognition.
Bibin Sam Paul SAntony Xavier GlittasGopalakrishnan LakshminarayananPublished in: Integr. (2021)
Keyphrases
- speech recognition
- low latency
- feature extraction
- cepstral coefficients
- speaker identification
- speech signal
- hidden markov models
- speech synthesis
- pattern recognition
- mel frequency cepstral coefficients
- language model
- real time
- automatic speech recognition
- speech recognizer
- high speed
- speech recognition systems
- speech recognition technology
- high throughput
- face recognition
- virtual machine
- gaussian mixture model
- highly efficient
- speaker recognition
- feature space
- speaker independent
- data mining
- extracted features
- distributed systems
- feature set
- feature vectors
- speaker diarization
- image processing
- feature selection
- machine learning