Thomas Fang Zheng

speaker verification (3) speaker embedding (3) replay attack (2) speaker recognition (2) low-rank adaptation (2) embedding learning (1) domain generalization (1) model quantization (1) emotion classification (1) probabilistic modeling (1) adversarial training (1) phone recognition (1) gaussian mixture model (1) marginal distribution (1) mixture of expert (1) automatic speech recognition (1) data sampling (1) feature aggregation (1) feature learning (1) model compression (1)