Hideki Kawahara
banner
hidekikawahara.bsky.social
Hideki Kawahara
@hidekikawahara.bsky.social
Auditory signal processing researcher.
This is my setup for a remote meeting. I also use nwmONE, an open-ear headphone, to monitor meeting sounds.
April 2, 2025 at 5:13 PM
This movie demonstrates an open-ear headphone. The sound was recorded by an omnidirectional miniature condenser microphone I am holding. I am exposed to a babble noise consisting of 20 speakers through headphones. The attenuation of the leakage sound exceeds 40dB under the 3 kHz frequency range.
March 28, 2025 at 9:58 AM
Open-ear headphones with ***PASSIVE*** acoustic circuits suppressing leakage sounds are a game-changer in speech communication research. I will present a technical report in Japanese at a virtual meeting. For your information, I found an English YouTube review (youtu.be/ppBwNsn4kEE).
February 25, 2025 at 8:20 PM
I made a similar (handy) enclosure for a one-inch full-range loudspeaker.
January 24, 2025 at 11:05 AM
I designed and printed an enclosure for a 1.5-inch full-range loudspeaker. The enclosure consists of three separable (screwed) parts. It is small and easy to bring around. I will have a lot of fun with this gadget.
January 24, 2025 at 5:16 AM
Maybe I am playing too much, but I learnt a lot. Very fast learning cycle with a 3D printer, a robot arm and MATLAB!
January 22, 2025 at 8:12 PM
I redesigned a microphone holder for sound field visualization and printed a head model for measuring an open-ear headphone mwn ONW by Sonority Inc. It is a fantastic gadget. It opens a new experimental paradigm for speech communication research.
January 17, 2025 at 9:19 AM
Reposted by Hideki Kawahara
@waspaa.com is on Bluesky!
Big changes are coming for WASPAA 2025!
WASPAA is moving, for the first time in its almost 40-year history. Stay tuned for the announcement of the new venue!
December 14, 2024 at 4:03 AM
Reposted by Hideki Kawahara
This is my first official post at Bluesky with great news :)

We got the best paper award at IEEE SLT'24! This work elegantly and straightforwardly solves contextual biasing issues with dynamic vocabulary arxiv.org/abs/2405.13344. Congrats, Yui, Yosuke, Shakeel, and Yifan!
! I'm super happy!
December 4, 2024 at 2:16 PM
Reposted by Hideki Kawahara
📣 #SpeechTech & #SpeechScience people

We are organizing a special session at #Interspeech2025 on: Interpretability in Audio & Speech Technology

Check out the special session website: sites.google.com/view/intersp...

Paper submission deadline 📆 12 February 2025
December 6, 2024 at 9:30 PM
Loud sounds! Interactive measurement of acoustic properties using several test sounds. The tool is accessible in my GitHub repository below.
github.com/HidekiKawaha...
A MATLAB live script makes any sounds relevant for acoustic measurement test signals.
interactiveSafeGuardingOCOCO.mlx
Have fun!
December 13, 2024 at 10:58 PM
RAPHSODIEE --> RHAPSODEE
I bought this. This can be a game changer in human speech communication research. But, I have to measure if it is true by using my RAPHSODIEE tools. Check links embedded in my COCOSDA presentation.
November 29, 2024 at 2:26 AM
I bought this. This can be a game changer in human speech communication research. But, I have to measure if it is true by using my RAPHSODIEE tools. Check links embedded in my COCOSDA presentation.
November 29, 2024 at 2:24 AM
Preview of my presentation at Cocosda 2024. The pdf copy of this presentation has links to related materials. drive.google.com/file/d/1x2vg...
November 16, 2024 at 4:38 PM