6 papers · 1 filter
Direct or Mediated? Task-Dependent Audio Information Routing in Large Audio Language Models
Yizhou Zhang, Wangjin Zhou, Xin Gu +6
Large Audio Language Models (LALMs) have demonstrated strong performance across a wide range of audio understanding tasks. However, they are typically evaluated on single, coherent…
Genre Bias or Aesthetic Perception? Identifying and Mitigating Shortcut Learning in Music Evaluation
Yizhou Zhang, Wangjin Zhou, Yi Zhao +3
Music aesthetics scoring plays a critical role in applications such as dataset curation, generative model evaluation, and reward modeling for music generation. Recent approaches re…
Rethinking Speech Foundation Model Fine-tuning: Better SFT or Better Match?
Wangjin Zhou, Yizhou Zhang, Yichi Wang +1
Supervised fine-tuning (SFT) is widely used to adapt self-supervised speech representations to downstream classification tasks. Small gains observed under a single pretrained check…
Position-Aware Target Speaker Extraction for Long-Form Multi-Party Conversations: A Diarization-Free Framework for ASR
Yichi Wang, Junzhe Chen, Wangjin Zhou +1
In long-form multi-party conversations, highly imbalanced speaker activity and frequent overlap make it difficult to identify "who spoke when and what". Sliding-window continuous s…
SONAR: Self-Distilled Continual Pre-training for Domain Adaptive Audio Representation
Yizhou Zhang, Yuan Gao, Wangjin Zhou +3
Self-supervised learning (SSL) on large-scale datasets like AudioSet has become the dominant paradigm for audio representation learning. While the continuous influx of new, unlabel…
Fusion of Self-supervised Learned Models for MOS Prediction
Zhengdong Yang, Wangjin Zhou, Chenhui Chu +4
We participated in the mean opinion score (MOS) prediction challenge, 2022. This challenge aims to predict MOS scores of synthetic speech on two tracks, the main track and a more c…