Hirofumi Nakajima — accepted AI-conference papers

2021

Fully-Online Always-Adaptation of Transfer Functions and Its Application to Sound Source Localization and Separation

Kazuhiro Nakadai, Masayuki Takigahira, Yusuke Kawai, Hirofumi Nakajima

IROS 2021poster

This paper addresses fully-online always-adaptation of a transfer function for robot audition systems based on microphone array processing. The transfer function represents signal propagation characteristics between a microphone and a sound source, which provides essential information for real-world…

Cited by 4 Source ↗Scholar ↗

2015

Non-linear distortion reduction for a loudspeaker based on recursive source equalization

Hirofumi Nakajima, Naoto Sakata, Kihiro Hashino

ICASSP 2015accepted

This paper proposes a method of reducing nonlinear distortion in sound reproduction systems by recursively equalizing input signals. The proposed method has lower computational costs and modeling errors compared with conventional methods. A computer simulation was undertaken to confirm these advanta…

Cited by 0 Source ↗Scholar ↗