Time-Delay-Neural-Network-Based Audio Feature Extractor for Ultra-Low Power Keyword Spotting.
Hiroshi FuketaPublished in: IEEE Trans. Circuits Syst. II Express Briefs (2022)
Keyphrases
- feature extractor
- keyword spotting
- speech processing
- ultra low power
- feature extraction
- speaker identification
- speech recognition
- signal processing
- low power
- hidden markov models
- multimedia
- recognition scheme
- printed documents
- texture descriptors
- feature values
- machine learning
- natural language processing
- multimedia systems
- feature selection
- computer vision
- power consumption
- real time
- multimedia information
- audio features
- pattern recognition