A combined CNN-LSTM Network for Audio Emotion Recognition using Speech and Song attributs.
Souha AyadiZied LachiriPublished in: ATSIP (2022)
Keyphrases
- emotion recognition
- audio features
- audio visual
- audio stream
- emotional speech
- audio files
- text to speech synthesis
- peer to peer
- network structure
- network traffic
- cellular neural networks
- multimedia
- speech processing
- acoustic features
- speaker identification
- broadcast news
- network model
- recurrent neural networks
- computer networks
- signal processing
- speech recognition
- speech music discrimination
- wireless sensor networks
- emotional state
- audio signals
- speech signal
- gaussian mixture model
- audio recordings
- multimodal fusion
- fixed point
- automatic transcription
- neural network
- cepstral features