Natural Language Dialog System Considering Speaker's Emotion Calculated from Acoustic Features.
Takumi TakahashiKazuya MeraTang Ba NhatYoshiaki KurosawaToshiyuki TakezawaPublished in: IWSDS (2016)
Keyphrases
- acoustic features
- natural language
- speaker verification
- emotion recognition
- automatic speech recognition
- music information retrieval
- visual features
- speech signal
- mel frequency cepstral coefficients
- machine learning
- speech recognition
- speaker recognition
- audio features
- audio visual
- cross correlation
- natural language processing
- human computer interaction
- facial expressions
- information extraction
- emotional state
- noisy environments
- neural network
- visual information
- language identification
- principal component analysis
- text data
- sentiment analysis