We are pleased to announce that Sony’s six research papers have been accepted to ICASSP, the international conference on acoustics, speech, and signal processing and machine learning.
ICASSP is the world's largest and most comprehensive international conference in the field of acoustics, speech, and signal processing and machine learning. Boasting a long history, its 46th edition will be held in 2021.
Sony’s Accepted Papers at ICASSP 2021: *Collaboration Partner
Adversarial Attacks on Audio Source Separation Naoya Takahashi, Shota Inoue*, Yuki Mitsufuji
*University of Tsukuba
All for One and One for All: Improving Music Separation by Bridging Networks Ryosuke Sawata, Stefan Uhlich, Shusuke Takahashi, Yuki Mitsufuji
End-to-end lyrics Recognition with Voice to Singing Style Transfer Sakya Basak*, Shrutina Agarwal*, Sriram Ganapathy*, Naoya Takahashi
*Indian Institute of Science
ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection Kazuki Shimada, Yuichiro Koyama, Naoya Takahashi, Shusuke Takahashi, Yuki Mitsufuji
Gaussian Kernelized Self-Attention for Long Sequence Data and its Application to CTC-Based Speech Recognition Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe*
*Johns Hopkins University
Making Punctuation Restoration Robust and Fast with Multi-Task Learning and Knowledge Distillation Michael Hentschel, Emiru Tsunoo, Takao Okuda