Gongping Huang

Achieving an impressive hierarchical F1 score of 81.25% through innovative multi-branch modeling and KNN post-processing reveals new potential in audio classification tasks.

WQ-Fusion achieves a remarkable score of 0.836 in cross-domain audio representation, showcasing the power of dynamic gated attention in feature selection.

Achieving a breakthrough in music source restoration, DTT-BSR+ significantly enhances signal quality while preserving semantic integrity, outperforming existing methods.

A two-stage framework for mispronunciation detection in low-resource Arabic achieves a groundbreaking F1-score of 0.7201, outperforming previous methods by over 63%.

Adaptive WNG estimation via deep learning leads to significant gains in speech enhancement performance over conventional methods.

Incorporating direction-of-arrival information, GC-Dec-IVA significantly enhances source separation in distributed microphone arrays, overcoming critical limitations of previous methods.

Current LALMs exhibit significant performance disparities across cognitive auditory capabilities, revealing a critical oversight in existing evaluation methods.

Achieve a 62.7% BLEU score boost in speech emotion captioning by offloading only the trickiest parts of the problem to the cloud.