yamakatz
@kyama0321.bsky.social
200 followers 160 following 33 posts
Auditory Signal Processing/Objective Metrics/Hearing Assistive Technologies. 
Twitter: @kyama0321
WEB: https://sites.google.com/site/kyama0321/en
Posts Media Videos Starter Packs
Pinned
kyama0321.bsky.social
I have released the new version of GammachirPy. The v234 model can simulate an auditory filter output with listeners' audiograms and compression healthiness🦻Moreover, the frame-based processing speed is 3x faster than the previous sample-based version🚗
github.com/kyama0321/ga...
Reposted by yamakatz
mdhk.net
Had such a great time presenting our tutorial on Interpretability Techniques for Speech Models at #Interspeech2025! 🔍

For anyone looking for an introduction to the topic, we've now uploaded all materials to the website: interpretingdl.github.io/speech-inter...
Reposted by yamakatz
interspeech2026.bsky.social
Don't forget to join in for the #interspeech2026 koala competition! interspeech2026.org/en-AU/pages/... #Interspeech2026KoalaCompetition
kyama0321.bsky.social
🇳🇱🌷🐨🇦🇺
#Interspeech2026KoalaCompetition
#Interspeech2026
#Interspeech2025
kyama0321.bsky.social
I finished my presentation. Thank you for attending the session and discussion! #Interspeech2025
kyama0321.bsky.social
🇳🇱🌷🐨🇦🇺
#Interspeech2026KoalaCompetition
#Interspeech2026
#Interspeech2025
kyama0321.bsky.social
#Interspeech2025
kyama0321.bsky.social
Bauquet at Stadshaven Brouwerij & Gastropub🍻🎸🥁🎺🎹⛴️ #Interspeech2025
kyama0321.bsky.social
I'll be presenting my paper at #Interspeech2025 :
Area6-Oral6-1330-1 “Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners"
www.isca-archive.org/interspeech_...
ISCA Archive - Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners
www.isca-archive.org
kyama0321.bsky.social
#Interspeech2025 opens!!🌷💃🕺🌷
kyama0321.bsky.social
I'm attending #Interspeech2025 in Rotterdam 🇳🇱
kyama0321.bsky.social
Our paper has been accepted for #Interspeech2025

Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners 🦻🐍

See you in Rotterdam🇳🇱
kyama0321.bsky.social
Our team's year-end party was held in Shibuya, Tokyo🍶 My colleagues gave me a wedding gift🎁 Thanks!
Reposted by yamakatz
serrjoa.bsky.social
Do you want to work with me for some months? Two internship positions available at the Music Team of Sony AI in Barcelona!
👇
Views from the office window. Photo taken just now.
kyama0321.bsky.social
Unfortunately, my paper for ICASSP 2025 was rejected🥺 Thanks to the reviewers and AC for the peer review🙏 I will work hard on my next submission, reflecting the useful comments I received on my research.
kyama0321.bsky.social
🤖👂 > SPS SLTC/AASP TECHNICAL COMMITTEE WEBINAR
Audio Signal Enhancement: A Weakly Supervised Deep Learning Approach
15 January 2025
Presented by Dr. Nobutaka Ito & Dr. Yoshiaki Bando
landing.signalprocessingsociety.org/jan-15-2024
IEEE SPS Webinars | 15 Jan 2025
Join us for an expert-led webinar to explore cutting-edge topics in signal processing. Register now and stay updated on upcoming events!
landing.signalprocessingsociety.org
Reposted by yamakatz
toni-tiler.bsky.social
A paper explaining how, in order to succeed in training a CLIP-like contrastive-based VL model, the alignment between the image and text encoders should be maintained
arxiv.org/abs/2412.04616
kyama0321.bsky.social
Donated to arXiv for open science🕊️
Reposted by yamakatz
jonathanleroux.bsky.social
IguanaTex v1.62 is out on GitHub.
If you're not familiar, IguanaTex is an add-in to insert LaTeX in PowerPoint (Windows/Mac).
Please consider adding a ⭐, we're getting close to 1k🤩
Alright, now back to my normal non-VBA life for a few months.

github.com/Jonathan-LeR...
Release v1.62 · Jonathan-LeRoux/IguanaTex
Summary v1.62 brings a few new features requested by users (Tectonic support, WSL support, generation from external file, default Fill color for Shape displays, export/import of settings to XML) an...
github.com