I am happy to share our new paper, `Learning Representations for New Sound Classes With Continual Self-Supervised Learning' arxiv.org/abs/2205.07390

Our paper 'Learning Representations for New Sound Classes With Continual Self-Supervised Learning' is accepted at IEEE Signal Processing Letters! Paper: arxiv.org/pdf/2205.07390… Code: github.com/zhepeiw/cssl_s… Zhepei Wang Mirco Ravanelli

We are very happy to share that our paper on unsupervised improvement of audio-text cross modal representations is accepted to WASPAA 2023! We will present the paper in SANE 2023 also! Preprint: export.arxiv.org/abs/2305.01864 #IEEE_WASPAA #SANE2023

GenAE: An audio autoencoder engineered for generative modeling. To appear at ICASSP 2026. w/ Ge Zhu Zhepei Wang Nicholas J. Bryan arXiv: arxiv.org/abs/2602.15749 Video: youtu.be/gDIIuLb0cf0