Learnable Sparse Filterbank for Speaker Verification.
Junyi PengRongzhi GuLadislav MosnerOldrich PlchotLukás BurgetJan CernockýPublished in: INTERSPEECH (2022)
Keyphrases
- image sequences
- speaker verification
- filter bank
- subband
- noisy environments
- speaker recognition
- multiscale
- multiresolution
- audio visual
- signal processing
- emotion recognition
- frequency domain
- video sequences
- spectral analysis
- wavelet bases
- wavelet basis
- computationally efficient
- learning algorithm
- image compression
- high dimensional
- multi modal
- image content
- wavelet transform
- using artificial neural networks
- feature vectors
- extracting features
- language identification
- feature space