Mel-Frequency Cepstral Coefficient (MFCC) for Music Feature Extraction for the Dancing Robot Movement Decision.
Indra Adji SulistijonoRenita Chulafa UrrosydaZaqiatud DarojahPublished in: ICIRA (2) (2016)
Keyphrases
- cepstral coefficients
- speech recognition
- audio features
- mel frequency cepstral coefficients
- audio signal
- linear prediction
- linear predictive
- sound source
- feature extraction
- feature set
- mobile robot
- speech signal
- hidden markov models
- music information retrieval
- human robot interaction
- decision making
- music retrieval
- audio signals
- speaker identification
- audio visual
- vision system
- low level
- humanoid robot
- language model
- image coding
- automatic speech recognition
- pattern recognition
- acoustic features
- autonomous robots
- decision makers
- robotic systems
- position and orientation
- robot arm
- decision problems
- robot manipulators
- visual features
- decision rules
- noisy environments
- cepstral features
- path planning
- feature vectors
- multi robot
- motion planning
- robot navigation
- lossless compression
- image classification
- speaker recognition
- robotic arm
- service robots
- subband
- pattern classification
- preprocessing
- multi modal
- non stationary