9 papers
Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages
Yang Xiao, Eun-Jung Holden, Ting Dang
Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challengin…
MoEScore: Mixture-of-Experts-Based Text-Audio Relevance Score Prediction for Text-to-Audio System Evaluation
Bochao Sun, Yang Xiao, Han Yin
Recent advances in generative models have enabled modern Text-to-Audio (TTA) systems to synthesize audio with high perceptual quality. However, TTA systems often struggle to mainta…
Continual Learning for Acoustic Event Classification
Yang Xiao
Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device acoustic event classification given the restrictions on computation resourc…
Evaluating Hydro-Science and Engineering Knowledge of Large Language Models
Shiruo Hu, Wenbo Shan, Yingjia Li +16
Hydro-Science and Engineering (Hydro-SE) is a critical and irreplaceable domain that secures human water supply, generates clean hydropower energy, and mitigates flood and drought…
SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts
Jiaqi Liu, Ronghao Fu, Lang Sun +6
The emergence of large vision-language models (VLMs) has significantly enhanced the efficiency and flexibility of geospatial interpretation. However, general-purpose VLMs remain su…
AFT: An Exemplar-Free Class Incremental Learning Method for Environmental Sound Classification
Xinyi Chen, Xi Chen, Zhenyu Weng +1
As sounds carry rich information, environmental sound classification (ESC) is crucial for numerous applications such as rare wild animals detection. However, our world constantly c…
LPGNet: A Lightweight Network with Parallel Attention and Gated Fusion for Multimodal Emotion Recognition
Zhining He, Yang Xiao
Emotion recognition in conversations (ERC) aims to predict the emotional state of each utterance by using multiple input types, such as text and audio. While Transformer-based mode…
Stereo sound event localization and detection based on PSELDnet pretraining and BiMamba sequence modeling
Wenmiao Gao, Yang Xiao
Pre-training methods have achieved significant performance improvements in sound event localization and detection (SELD) tasks, but existing Transformer-based models suffer from hi…
Advancing Airport Tower Command Recognition: Integrating Squeeze-and-Excitation and Broadcasted Residual Learning
Yuanxi Lin, Tonglin Zhou, Yang Xiao
Accurate recognition of aviation commands is vital for flight safety and efficiency, as pilots must follow air traffic control instructions precisely. This paper addresses challeng…