Introducing the COVID-19 YouTube (COVYT) speech dataset featuring the same speakers with and without infection.
Andreas TriantafyllopoulosAnastasia SemertzidouMeishu SongFlorian B. PokornyBjörn W. SchullerPublished in: Biomed. Signal Process. Control. (2024)
Keyphrases
- speech recognition
- speech signal
- benchmark datasets
- speaker dependent
- social media
- action recognition
- automatic speech recognition
- audio visual
- speech recognizer
- hidden markov models
- space time interest points
- feature selection
- sir model
- dynamical behavior
- immune response
- dialogue system
- human actions
- feature set
- multimedia