arXiv subjects

Jialing Wang

Publications and source records attributed to Jialing Wang.

3 recordsLinked to original sources

arXiv2026

Ti-Audio: The First Multi-Dialectal End-to-End Speech LLM for Tibetan

Recent advances in Speech Large Language Models (Speech-LLMs) have made significant progress, greatly enhancing multimodal interaction capabilities.However, their application in low-resource and dialect-diverse environments still faces challenges. The severe scarcity of Tibetan data, coupled with the phonetic differences among its major dialects (\"U-Tsang, Amdo, and Kham), is a prime example of this challenge. This paper proposes Ti-Audio, the first multi-dialectal end-to-end Speech-LLM for Tibetan. To efficiently align speech and text, we introduce a Dynamic Q-Former Adapter that extracts essential acoustic features from variable-length speech, ensuring stable cross-modal alignment even with limited data. At the data level, we leverage mutual assistance among related dialects to alleviate data scarcity and employ a temperature-based sampling strategy to maximize this synergy. Experimental results demonstrate that Ti-Audio achieves state-of-the-art performance on Tibetan benchmarks for automatic speech recognition and speech translation. Our work validates the effectiveness of cross-dialectal cooperation and provides a scalable paradigm for the development of Speech-LLM in low-resource scenarios.

cs.SD↗

arXiv2024

MI 2 MI: Training Dyad with Collaborative Brain-Computer Interface and Cooperative Motor Imagery Tasks for Better BCI Performance

Collaborative brain-computer interface (cBCI) that conduct motor imagery (MI) among multiple users has the potential not only to improve overall BCI performance by integrating information from multiple users, but also to leverage individuals' performance in decision-making or control. However, existed research mostly focused on the brain signals changes through a single user, not noticing the possible interaction between users during the collaboration. In this work, we utilized cBCI and designed a cooperative four-classes MI task to train the dyad. A humanoid robot would stimulate the dyad to conduct both left/right hand and tongue/foot MI. Single user was asked to conduct single MI task before and after the cooperative MI task. The experiment results showed that our training could activate better performance (e.g., high quality of EEG /MI classification accuracy) for the single user than single MI task, and the single user also obtained better single MI performance after cooperative MI training.

cs.HC↗

arXiv2018

Second-order linear structure-preserving modified finite volume schemes for the regularized long-wave equation

In this paper, based on the weak form of the Hamiltonian formulation of the regularized long-wave equation and a novel approach of transforming the original Hamiltonian energy into a quadratic functional, a fully implicit and three linear-implicit energy conservation numerical schemes are respectively proposed. The resulting numerical schemes are proved theoretically to satisfy the energy conservation law in the discrete level. Moreover, these linear-implicit schemes are efficient in practical computation because only a linear system need to be solved at each time step. The proposed schemes are both second order accurate in time and space. Numerical experiments are presented to show all the proposed schemes have satisfactory performance in providing accurate solution and the remarkable energy-preserving property.

math.NA↗