Lecturer | Shanxi Agricultural University | China
Ms. Yaqin Wu is a dedicated researcher with specialized expertise in acoustic signal analysis, deep learning, and multimodal information fusion. Yaqin is adept in Python, MATLAB, MySQL, and Linux systems. Their academic and project experience spans both voice signal processing and intelligent animal behavior monitoring. Yaqin has led and participated in several impactful projects, including the development of an automatic pathological voice disorder detection system (2022–2023), a MATLAB-based ideological education initiative, and a master’s thesis on pathological voice restoration algorithms, which involved advanced techniques like multi-tone signal processing and speech synthesis. They contributed to AVS audio codec development and handled multiple modules including G.729 codec optimization. Notably, Yaqin is involved in pioneering multimodal deep learning projects for health and behavior monitoring in livestock, combining audio and video data to detect issues like coughing and feeding irregularities. Their work has also extended to calf diarrhea behavior detection using asynchronous multimodal fusion. Recognized for academic excellence and leadership, Yaqin has received multiple honors, including the “Outstanding Achievement Award” for their master’s thesis, first prizes in science and mathematics competitions, and numerous scholarships and commendations across institutions. To date, Yaqin Wu has published 9 documents, received 80 citations, and holds an h-index of 3, reflecting a growing impact in the fields of signal processing and intelligent monitoring systems.
Profile: Scopus
Featured Publication
1. GBNF-VAE: A pathological voice enhancement model based on gold section for bottleneck feature with variational autoencoder.
Cited by: 2
