Intelligent Media Processing Research Team

We will present a demo "What does your voice sound like?" on the AIST Open Day 2024 at AIST Tokyo Waterfront.
Saturday, October 26th, 2024 10am～4pm Last admission 3:30pm

Yoshihiro Sato, Satoru Fukayama, and Jun Ogata will be presenting at the Seismological Society of Japan, Fall Meeting 2022.
Fault Plane Estimation from 3D Hypocenter Distribution by Two-step Clustering Considering Local Shapes

Hiroki Karatsu, Satoru Fukayama will be presenting at IPSJ SIGMUS 135th meeting. 
Evaluation of Data Augmentation for DeepBach-based Automatic Four-part Harmonisation

Kentaro Onda, Satoru Fukayama, Daisuke Saito, and Nobuaki Minematsu, "Advanced Modeling of Interlanguage Speech Intelligibility Benefit with L1-L2 Multi-Task Learning Using Differentiable K-Means for Accent-Robust Discrete Token-Based ASR," in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2026.

Kohei Asai, Wataru Nakata, Yuki Saito, and Hiroshi Saruwatari, "Geneses: Unified generative speech enhancement and separation," in Proceedings of The Joint Workshop on HSCMA and CHiME 2026 (IEEE ICASSP2026 Satellite Workshop), May 2026.

Kanami Imamura, Tomohiko Nakamura, Kohei Yatabe, and Hiroshi Saruwatari, "Dissecting performance degradation in audio source separation under sampling frequency mismatch," in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2026.