Vocal92: Audio Dataset With a Cappella Solo Singing and Speech.
Zhuo DengRuohua ZhouPublished in: IEEE Access (2023)
Keyphrases
- acoustic features
- audio features
- emotion recognition
- speech signal
- audio stream
- music information retrieval
- audio visual
- feature set
- automatic speech recognition
- speaker verification
- visual features
- speaker identification
- broadcast news
- audio signals
- mel frequency cepstral coefficients
- speech recognition
- human computer interaction
- benchmark datasets
- audio signal
- cepstral features
- low level
- signal processing
- database
- automatic transcription
- probabilistic model
- prosodic features
- digital audio
- visual speech
- speech synthesis
- pattern recognition
- image retrieval
- spontaneous speech
- audio video
- noisy environments
- multi stream
- feature vectors
- text to speech
- speaker recognition
- synthetic datasets
- digital video