2 papers
cs.SD2026
The T12 System for AudioMOS Challenge 2025: Audio Aesthetics Score Prediction System Using KAN- and VERSA-based Models
Katsuhiko Yamamoto, Koichi Miyazaki, Shogo Seki
We propose an audio aesthetics score (AES) prediction system by CyberAgent (AESCA) for AudioMOS Challenge 2025 (AMC25) Track 2. The AESCA comprises a Kolmogorov--Arnold Network (KA…
cs.SD2025
Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners
Katsuhiko Yamamoto, Koichi Miyazaki
Speech intelligibility prediction (SIP) models have been used as objective metrics to assess intelligibility for hearing-impaired (HI) listeners. In the Clarity Prediction Challeng…