DASB - Discrete Audio and Speech Benchmark.
Pooneh MousaviLuca Della LiberaJarod DuretArtem PloujnikovCem SubakanMirco RavanelliPublished in: CoRR (2024)
Keyphrases
- audio stream
- audio visual
- broadcast news
- audio signals
- emotion recognition
- speaker identification
- text to speech
- speech processing
- audio features
- cepstral features
- multimedia
- digital audio
- prosodic features
- speech recognition
- audio recordings
- audio video
- linear predictive coding
- multi modal
- automatic transcription
- speech music discrimination
- speech synthesis
- automatic speech recognition
- audio signal
- multi stream
- spoken documents
- acoustic signals
- visual information
- low level
- speaker verification
- probabilistic model
- language model
- signal processing
- audio visual speech recognition
- speech corpus
- finite number
- noisy environments
- visual speech
- spontaneous speech
- content based video retrieval
- spoken language