Mel-Frequency Cepstral Coefficients-Based Emotion Identification Using Artificial Neural Network From Speech And Songs.
Ishan DhakalNavin Kumar SahKwok Wei LingSweety Kumari RauniyarGaurav KumarMahesh T. RPublished in: ICCCNT (2023)
Keyphrases
- using artificial neural networks
- acoustic features
- mel frequency cepstral coefficients
- speaker verification
- audio features
- speech signal
- speaker recognition
- speaker identification
- music information retrieval
- linear predictive
- emotion recognition
- automatic speech recognition
- speech recognition
- artificial neural networks
- audio visual
- emotion classification
- visual features
- feature vectors
- gaussian mixture model
- low level
- cepstral coefficients
- pattern recognition
- audio signal
- genetic algorithm
- facial expressions
- broadcast news
- finite element analysis
- principal component analysis
- emotional state
- multi modal
- noisy environments
- information retrieval
- cross correlation
- speaker diarization
- high level
- text data
- neural network model
- visual information