Shanshan Wang (王珊珊)

I am a PhD student in Machine Listening and Audio Research Group(ARG) from Tampere University. I am working in collaboration with assistant professor Annamaria Mesaros and professor Tuomas Virtanen. My research interests include audio-visual feature learning, self-supervised learning, audio signal processing, and general deep Learning. My complete academic information can be found in curriculum vitae.

• 12.04 - 19.04, 2024, will present our recent work in Seoul, South Korea, ICASSP2024

• Playing around generative models, check out videos on me speaking in Spanish, Russian, Hindi, Finnish, Greek, and Romanian.

• 12, 2023, received Huawei award for best PhD publications

• 14.04 - 31.07, 2023, worked as an intern in Huawei, Finland

• 04.06 - 10.06, 2023, presented our recent work in Rhodes Island, Greece, ICASSP2023

• 23.10, 2022, presented our recent journal work in ECCV2022 workshop AV4D: Visual Learning of Sounds in Spaces, Youtube link

• Served as a reviewer for DCASE2022 and ECCV2022 workshop VOLI

• 23.08 - 27.08, 2021, selected as one of the ten finalists of the 3 Minute Thesis (3MT) contest, check my PhD thesis contest video Youtube link

• 01.03 - 01.07,2021, one of the coordinators in DCASE2021 task1 subtaskb, DCASE2021

• 02.2020 - present, PhD student at Tampere University

• S. Wang, S. Tripathy, T. Heittola, and A. Mesaros, "Positive and negative sampling strategies for self-supervised learning on audio-video data", in 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing workshop(ICASSP 2024): Code, Paper, poster.

• S. Wang, S. Tripathy, and A. Mesaros, "Self-supervised learning of audio representations using angular contrastive loss", in 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023): Code, Paper, and Youtube link.

• S. Wang, A. Politis, A. Mesaros and T. Virtanen, "Self-supervised learning of audio representations from audio-visual data using spatial alignment", in ECCV2022 workshop: Workshop link, Youtube link.

• S. Wang, A. Politis, A. Mesaros and T. Virtanen, "Self-supervised learning of audio representations from audio-visual data using spatial alignment", in IEEE Journal of Selected Topics in Signal Processing (JSTSP), 2022: Paper.

• S. Wang, A. Mesaros, T. Heittola and T. Virtanen, "Audio-visual scene classification: analysis of DCASE 2021 Challenge submissions", 2021: Paper, Youtube link.

• S. Wang, G. Naithani, A Politis, and T. Virtanen, "Deep neural network Based Low-latency Speech Separation with Asymmetric analysis-Synthesis Window Pair", in EUSIPCO, 2021: Paper, Code, Youtube link.

• S. Wang, A. Mesaros, T. Heittola and T. Virtanen, "A Curated Dataset of Urban Scenes for Audio-Visual Scene Analysis," in Proc. ICASSP, 2021: Paper, Code, Youtube link.

• S. Wang, G. Naithani, and T. Virtanen, “Low-latency deep clustering for speech separation,” in Proc. ICASSP, 2019: Paper, Code, Youtube link.

Graduation: 12.2019, Thesis

Address: Tampere University, Hervanta Campus, Tietotalo, Room No: TF405
Email: shanshan.wang@tuni.fi