The anomalous sound detection seminar will also be streamed on Zoom! Please register if you are interested in! forms.gle/fgLrVtc7iBWkgM…

#DCASE2024 workshop is ready💪

Surprise of the day. Manjunath Mulimani and I got the best paper award in DCASE Workshop! The work was funded by Jane and Aatos Erkko Foundation.

The anomalous sound detection seminar with Kevin Wilkinghoff and Takuya Fujimura is being held tomorrow in Kyoto!

Thank you for participating in #DCASE2024 workshop. Your participation made it a meaningful experience, and we look forward to staying connected.

#DCASE2025 workshop goes to Barcelona🎉

Thank you for having inspiring seminar talks! We spent a great time with Kevin and Takuya at an izakaya restaurant after the seminar!

Our paper entitled "Onset-and-Offset-Aware Sound Event Detection via Differentiable Frame-to-Event Mapping" is accepted for IEEE Signal Processing Letters! Congulatulations Yoshinaga-kun!🎉🎉🎉

今月号の日本音響学会誌80巻12号に寄稿した環境音合成に関する解説記事が公開されました！同志社大学の井本先生 (KeisukeImoto)と共同執筆です。 統計的手法による環境音・効果音合成の基礎から評価方法、データセット、最新の研究動向まで広く解説しました。 是非みなさんご一読ください🙇🏻‍♂️

Our paper has been accepted to #ICASSP2025 🎉 "Formula-Supervised Sound Event Detection: Pre-Training Without Real Data" Many thanks to my outstanding co-authors!!! Keitaro Tanaka Yoshiaki Bando imotts Hirokatsu Kataoka | 片岡裕雄 慶應義塾大学理工学部青木研究室（Yoshimitsu Aoki）

#ICASSP2025 に採択されました🎉🎉🎉 実データ不要でSound Event Detectionの事前学習を実施しています。 数式ドリブン教師あり学習（FDSL）を聴覚機能拡張にも展開する時が来ました！

I am joining Meta GenAI Speech team as a research scientist! Excited to contribute to advancing speech LLaMA models!🦙

We are thrilled to recognize the many #womenwholead in the Signal Processing Society like Dr. Shoko Araki whose work has contributed to advances in blind audio source separation and more. ⚡Learn more at hubs.la/Q03bJdBx0. #womenshistorymonth #signalprocessing #IEEE

``Formula-Supervised Sound Event Detection: Pre-Training Without Real Data,'' Yuto Shibata, Keitaro Tanaka, Yoshiaki Bando, Keisuke Imoto, Hirokatsu Kataoka, Yoshimitsu Aoki, ift.tt/vOGc3yC

We are happy that🦉 OWLS, 18B to 0.25B open ASR/AST limited data scaling laws, has been accepted to ICML Conference 2025 led by William Chen Jinchuan Tian (田晋川) from Shinji Watanabe WAVLab | @CarnegieMellon and NVIDIA AI Models: huggingface.co/collections/es… Paper: arxiv.org/pdf/2502.10373 Deepspeed ESPNet:

We are holding a competition for the automatic evaluation of text-to-audio generation. We will evaluate the semantic alignment between text and audio. Please join us! Pre-registration:forms.gle/s5pNf72Z7KWCfS… *Pre-registration does not obligate you to participate in competition

📢 The results for most of the tasks of DCASE 2025 challenge are out! dcase.community/challenge2025/

Our paper got accepted to IEEE WASPAA 2025! Huge thanks and congrats to my co-authors🎉

Our paper "Context-Aware Query Refinement for Target Sound Extraction: Handling Partially Matched Queries" has been accepted to IEEE WASPAA 2025!🎉 Huge thanks to KeisukeImoto for incredible support. #WASPAA2025

The First XACLE Challenge has been accepted as the ICASSP2026 SP Grand Challenge🎉 IEEE ICASSP