GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition.
Yu PanYanni HuYuguang YangWen FeiJixun YaoHeng LuLei MaJianjun ZhaoPublished in: ICASSP (2024)
Keyphrases
- speech emotion recognition
- programming language
- natural language
- high accuracy
- human language
- text to speech
- signal processing
- multimedia
- computationally efficient
- language learning
- high quality
- information retrieval
- audio features
- target language
- multi modal
- audio stream
- specification language
- audio visual
- visual information
- neural network
- query language
- image retrieval
- decision trees
- machine learning