Toxic Speech and Speech Emotions: Investigations of Audio-based Modeling and Intercorrelations.
Wei-Cheng LinDimitra EmmanouilidouPublished in: EUSIPCO (2022)
Keyphrases
- emotion recognition
- audio visual
- audio stream
- speech recognition
- text to speech
- broadcast news
- speaker identification
- speech synthesis
- cepstral features
- audio signals
- speech signal
- recognition engine
- endpoint detection
- speech processing
- emotional speech
- multimedia
- audio features
- linear predictive coding
- multi stream
- digital audio
- human language
- automatic speech recognition
- spontaneous speech
- emotion classification
- acoustic signals
- human communication
- prosodic features
- spoken document retrieval
- acoustic features
- human computer interaction
- content based video retrieval
- audio video
- speaker recognition
- language acquisition
- spoken documents
- signal processing
- automatic transcription
- feature set
- hidden markov models