Improving Emotion Identification Using Phone Posteriors in Raw Speech Waveform Based DNN.
Mousmita SarmaPegah GhahremaniDaniel PoveyNagendra Kumar GoelKandarpa Kumar SarmaNajim DehakPublished in: INTERSPEECH (2019)
Keyphrases
- emotional speech
- emotion recognition
- text to speech synthesis
- speech recognition
- emotional state
- speech synthesis
- spoken term detection
- emotion classification
- acoustic models
- mobile phone
- audio visual
- facial expressions
- raw data
- cross correlation
- markov networks
- language acquisition
- multi modal
- markov random field
- feature extraction