Cutting Edge
ソニー、音声・音響信号処理、機械学習理分野で 世界最大の
国際学会「ICASSP 2021」にて6本の論文採択
ソニー株式会社はこの度、音声・音響信号処理、機械学習分野における国際学会「ICASSP」にて6本の論文が採択されました。
ICASSP (International Conference on Acoustics, Speech, and Signal Processing)は、音声・音響信号処理、機械学習分野における世界最大の国際会議で、2021年は46回目の開催となる非常に歴史の長い権威あるカンファレンスです。
採択された論文:*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