IEEE Signal Processing Society (SPS) Tokyo Joint Chapter
[主催行事]
[共催行事]
[協賛行事]
[表彰]
[役員]
[English]
新着情報
- 第6回 IEEE Signal Processing Society (SPS) Japan Young Author Best Paper Awardは、選考の結果、以下の論文に受賞が決定しました（太字が受賞者）。おめでとうございます！
- R. Yamamoto, E. Song, and J.-M. Kim, "Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram," Proc. ICASSP, 2020, pp. 6199--6203.
- A.A. Nugraha, A. Liutkus, and E. Vincent, "Multichannel audio source separation with deep neural networks," IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 24, No. 9, pp. 1652-1664, 2016.
- 第15回 IEEE Signal Processing Society (SPS) Japan Student Journal Paper AwardおよびIEEE Signal Processing Society (SPS) Japan Student Conference Paper Awardは、選考の結果、以下の論文に受賞が決定しました（太字が受賞者）。おめでとうございます！
- Journal部門 ("IEEE SPS Japan Student Journal Paper Award")
- Y. Masuyama, K. Yatabe, Y. Koizumi, Y. Oikawa, and N. Harada, "Deep Griffin-Lim iteration: Trainable iterative phase reconstruction using neural network," IEEE Journal of Selected Topics in Signal Processing, Vol. 15, No. 1, pp. 37-50, 2021.
- W. Kim, A. Kanezaki, and M. Tanaka, "Unsupervised learning of image segmentation based on differentiable feature clustering," IEEE Transactions on Image Processing, Vol. 29, pp. 8055-8068, 2020.
- K. Sekiguchi, Y. Bando, A.A. Nugraha, K. Yoshii, and T. Kawahara, "Fast multichannel nonnegative matrix factorization with directivity-aware jointly-diagonalizable spatial covariance matrices for blind source separation," IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 28, pp. 2610-2625, 2020.
- Conference部門 ("IEEE SPS Japan Student Conference Paper Award")
- Y. Hono, S. Takaki, K. Hashimoto, K. Oura, Y. Nankaku, and K. Tokuda, "Periodnet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components," ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6049-6053, 2021.
- W. Sirichotedumrong, T. Maekawa, Y. Kinoshita, and H. Kiya, "Privacy-preserving deep neural networks with pixel-based image encryption considering data augmentation in the encrypted domain," 2019 IEEE International Conference on Image Processing (ICIP), pp. 674-678, 2019.
- K. Tanaka, R. Nishikimi, Y. Bando, K. Yoshii, S. Morishima, "Pitch-timbre disentanglement of musical instrument sounds based on VAE-based metric learning," 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 111-115, 2021.
- 第4回IEEE Signal Processing Society (SPS) Tokyo Joint Chapter Student Awardは、選考の結果、以下の論文に受賞が決定しました（太字が受賞者）。おめでとうございます！
- E. Yamagata and S. Ono "A constrained alternating minimization approach to end-to-end graph signal denoising," IEICE Tech. Rep. vol. 120, no. 398, SIP2020-90, pp. 1-4, March 2021.
- 児玉侑也, 村松正吾, 山田寛喜, "二次元ベクトル場のためのℓ2 ノルム固定小数点演算－ 等方性全変動と複素絶対値 －," 第34回 信号処理シンポジウム, pp. 22--27, 2019.
- 岡本悠希，井本桂右，高道慎之介，山西良典，福森隆寛，山下洋一, "Onoma-to-wave: オノマトペを利用した環境音合成手法の提案," 日本音響学会2021年春季研究発表会, pp. 843-846, 2021.
-
講演会
講演者：Dr. Zhuo Chen (Microsoft Could & AI)
日時：2020年12月17日(木) 15:00～16:30
会場：オンライン開催（CISCO WebEXを用いたビデオ会議形式）：このリンクから参加登録してください
講演題目：Speech Recognition and Diarization for Unsegmented Multi-talker Recordings with Speaker Overlaps
言語：英語
講演概要
As a natural phenomenon often observed in conversation, overlapped speech significantly degrades the performance of speech recognition and diarization. This has long hindered wider use of automatic speech recognition technologies in our daily lives. To tackle this problem, in recent years, drastic progress has been made in overlapped speech processing, starting from toy examples towards realistic conversation recordings. In particular, this research topic was extensively studied at this year's Jelinek summer workshop organized by Johns Hopkins University, where researchers world-widely gathered virtually for about 7 weeks, and extensively exchanged ideas on the current state-of-the-art and the new directions. In this talk, I will give a refreshed perspective of the problem, including its problem definition, background, challenges and recent trends observed from the workshop. Then I will give an in-depth introduction on recent technological advances brought by our Microsoft speech team, including the speech separation algorithms for long recording processing and its integration with real world conversation transcription systems. Lastly, I will introduce several recent attempts in modeling the long span overlapped speech in an end to end fashion. -
Distinguished Lecturer講演会
講演者：Prof. Andrea Cavallaro (Queen Mary University of London, UK)
日時：2020年12月10日（木）18:00～19:00
会場：オンライン開催（Zoomウェビナーを用いたビデオ会議形式）：このリンクから参加登録してください
講演題目：Adversarial attacks on image classifiers
言語：英語
講演概要
Images we share online reveal information about personal choices and preferences, which can be inferred by classifiers. To prevent privacy violations and to protect the visual content from unwanted automatic inferences, I discuss how to exploit the vulnerability of classifiers to adversarial attacks to craft perturbations that maintain (and even improve) image quality. As adversarial perturbations designed to protect visual content against classifiers may be ineffective against classifiers that were not seen during the generation of the perturbation or against defences that use re-quantization or image compression, I will discuss how to craft perturbations based on randomised ensembles to make them robust to defences, on image semantics to selectively modify colours within chosen ranges that are perceived as natural by humans, and on perturbations that enhance image details. -
Distinguished Industrial Speaker講演会
講演者：Dr. Akihiko Sugiyama (IEEE Fellow, Yahoo! Japan)
日時：2020年11月27日（金）15:00～17:00
会場：オンライン開催（CISCO WebEXを用いたビデオ会議形式）：このリンクから参加登録してください
講演題目：Signal Enhancement in Consumer Products
言語：日本語
講演概要
This lecture presents the A to Z of signal enhancement when it is applied to consumer products such as cellphone handsets, digital still cameras and camcorders, PCs and tablet computers, TV receivers, and gaming controllers. Starting from basic single channel signal enhancement in the frequency domain, it continues on to two-channel processing and multi-channel processing also known as microphone arrays. Types of noise to be covered include environmental noise, mechanical noise, impact (or transient) noise and wind noise. Problems and solutions that include recent topics are discussed for each application from a viewpoint of the algorithm and implementation. Sound demonstrations will be provided to help audience understand the effect of solutions.
活動内容
主催
- 講演会
-
Distinguished Industrial Speaker講演会
講演者：Dr. Akihiko Sugiyama (IEEE Fellow, Yahoo! Japan)
日時：2020年11月27日（金）15:00～17:00
会場：オンライン開催（CISCO WebEXを用いたビデオ会議形式）：このリンクから参加登録してください
講演題目：Signal Enhancement in Consumer Products
- 国際会議・シンポジウム・ワークショップ
- 研究会
- その他
共催
- 講演会
- 国際会議・シンポジウム・ワークショップ
- 研究会
- その他
協賛
- 講演会
- 国際会議・シンポジウム・ワークショップ
-
第35回信号処理シンポジウム (協賛)
(2020年11月4日-6日; 高知会館（オンラインでの開催を検討中）) -
The 52nd ISCIE International Symposium on Stochastic Systems Theory and Its Applications (SSS '20) (協賛)
(2020年10月29日-30日; Osaka University Convention Center) -
第33回 回路とシステムワークショップ (協賛)
(2020年8月20日; オンライン) - 研究会
- その他
共催、協賛などのご相談はSecretaryまでメールにてお願い致します．
表彰
- IEEE SPS Japan Young Author Best Paper Award
投稿時に40歳未満のIEEE SPS会員が筆頭著者である，IEEE SPSに関連する論文誌や国際会議で発表された論文が対象
- IEEE SPS Japan Student Journal Paper Award
IEEE SPS Japan Student Conference Paper Award
投稿時に学生であるIEEE SPS会員が筆頭著者である，IEEE SPSに関連する論文誌や国際会議で発表された論文が対象
- IEEE SPS Tokyo Joint Chapter Student Award
投稿時に学生であるIEEE SPS Tokyo Joint Chapter所属会員が筆頭著者である，日本国内の信号処理関連の学会で発表された査読無し発表論文が対象
- IEEE SPS Japan Student Demonstration Award
IEEE SPSの学生会員が筆頭著者である，DSPS教育会議で発表されたデモンストレーション発表が対象 (現在は募集していません）
お問い合わせはSecretaryまでメールにてお願い致します．
リンク
役員
- Chair: 篠田 浩一 (Shinoda, Koichi)
東京工業大学 - Vice Chair: 小野 順貴 (Nobutaka, Ono)
東京都立大学 - Secretary: 鷲沢 嘉一 (Washizawa, Yoshikazu)
電気通信大学 - Treasurer: 小山 翔一 (Koyama, Shoichi)
東京大学