WeCanTalk: A New Multi-language, Multi-modal Resource for Speaker Recognition.
Karen JonesKevin WalkerChristopher CarusoJonathan WrightStephanie M. StrasselPublished in: LREC (2022)
Keyphrases
- multi modal
- speaker recognition
- gaussian mixture model
- audio visual
- speaker verification
- vector quantization
- probabilistic neural network
- semantic concepts
- speaker identification
- multi modality
- speech signal
- image annotation
- speech recognition
- video search
- k means
- single modality
- high dimensional
- uni modal
- language processing
- generative model
- expectation maximization
- multiresolution
- feature vectors