EMO-AVSR: Two-Level Approach for Audio-Visual Emotional Speech Recognition.
Denis IvankoElena RyuminaDmitry RyuminAlexandr AxyonovAlexey M. KashevnikAlexey KarpovPublished in: SPECOM (1) (2023)
Keyphrases
- audio visual
- speech recognition
- emotion recognition
- audio visual speech recognition
- multi modal
- affective states
- hidden markov models
- speech recognizer
- speech synthesis
- language model
- visual information
- multi stream
- pattern recognition
- speech signal
- speaker verification
- multimedia
- visual data
- automatic speech recognition
- digit recognition
- audio features
- noisy environments
- speech recognition systems
- non stationary
- information retrieval