Detection and classification of acoustic scenes and events

AST-SED: an Effective Sound Event Detection Method Based on Audio Spectrogram Transformer

DATASET BALANCING CAN HURT MODEL PERFORMANCE

BEANS: The Benchmark of Animal Sounds

Efficient similarity-based passive filter pruning for compressing CNNs

AVES: Animal Vocalization Encoder based on Self-Supervision

Diverse and Vivid Sound Generation from Text Descriptions

A NOVEL METRIC FOR EVALUATING AUDIO CAPTION SIMILARITY

BTS-E: Audio Deepfake Detection using Breathing-Talking-Silence Encoder