model compression

ST-MFNET MINI: KNOWLEDGE DISTILLATION-DRIVEN FRAME INTERPOLATION

ACP: ADAPTIVE CHANNEL PRUNING FOR EFFICIENT NEURAL NETWORKS

SPARSEBFA: ATTACKING SPARSE DEEP NEURAL NETWORKS WITH THE WORST-CASE BIT FLIPS ON COORDINATES

Compressing Transformer-based ASR Model by Task-driven Loss and Attention-based Multi-level Feature Distillation

SELF-KNOWLEDGE DISTILLATION VIA FEATURE ENHANCEMENT FOR SPEAKER VERIFICATION

DISTILHUBERT: SPEECH REPRESENTATION LEARNING BY LAYER-WISE DISTILLATION OF HIDDEN-UNIT BERT

PART-OF-SPEECH MODELS COMPRESSION METHODS FOR ON-DEVICE GRAPHEME-TO-PHONEME CONVERSION

Data Agnostic Filter Gating for Efficient Deep Networks

BLOOM-NET: BLOCKWISE OPTIMIZATION FOR MASKING NETWORKS TOWARD SCALABLE AND EFFICIENT SPEECH ENHANCEMENT

DYNAMICALLY PRUNING SEGFORMER FOR EFFICIENT SEMANTIC SEGMENTATION