activity
20242026
collaborators

15 papers

cs.SD2026

Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement

Szu-Wei Fu, Rong Chao, Xuesong Yang +6

Universal Speech Enhancement (USE) aims to restore speech quality under diverse degradation conditions while preserving signal fidelity. Despite recent progress, key challenges in…

eess.AS2026

Few-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language Models

Ryandhimas E. Zezario, Dyah A. M. G. Wisnu, Szu-Wei Fu +3

In this paper, we introduce GatherMOS, a novel framework that leverages large language models (LLM) as meta-evaluators to aggregate diverse signals into quality predictions. Gather…

eess.AS2026

MOS-Bias: From Hidden Gender Bias to Gender-Aware Speech Quality Assessment

Wenze Ren, Yi-Cheng Lin, Wen-Chin Huang +5

The Mean Opinion Score (MOS) serves as the standard metric for speech quality assessment, yet biases in human annotations remain underexplored. We conduct the first systematic anal…

eess.AS2025

STSM-FiLM: A FiLM-Conditioned Neural Architecture for Time-Scale Modification of Speech

Dyah A. M. G. Wisnu, Ryandhimas E. Zezario, Stefano Rini +4

Time-Scale Modification (TSM) of speech aims to alter the playback rate of audio without changing its pitch. While classical methods like Waveform Similarity-based Overlap-Add (WSO…

eess.AS2025

Speech Intelligibility Assessment with Uncertainty-Aware Whisper Embeddings and sLSTM

Ryandhimas E. Zezario, Dyah A. M. G. Wisnu, Hsin-Min Wang +1

Non-intrusive speech intelligibility prediction remains challenging due to variability in speakers, noise conditions, and subjective perception. We propose an uncertainty-aware app…

eess.AS2025

Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings

Dyah A. M. G. Wisnu, Ryandhimas E. Zezario, Stefano Rini +2

We present a system for automatic multi-axis perceptual quality prediction of generative audio, developed for Track 2 of the AudioMOS Challenge 2025. The task is to predict four Au…