4 papers
Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
Jinchuan Tian, Haoran Wang, Bo-Hao Su +14
Current audio foundation models typically rely on rigid, task-specific supervision (e.g., speech recognition), addressing isolated factors of audio rather than the whole. In contra…
ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools -- From Consensus Learning to Ambiguity-Driven Emotion Reasoning
Esther Sun, Bo-Hao Su, Abinay Reddy Naini +2
Speech Large Language Models (SLLMs) enable high-level emotion reasoning but often produce ungrounded, text-biased judgments without verifiable acoustic evidence. In contrast, self…
Reasoning Beyond Majority Vote: An Explainable SpeechLM Framework for Speech Emotion Recognition
Bo-Hao Su, Hui-Ying Shih, Jinchuan Tian +4
Speech Emotion Recognition (SER) is typically trained and evaluated on majority-voted labels, which simplifies benchmarking but masks subjectivity and provides little transparency…
ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation
Jiatong Shi, Yifan Cheng, Bo-Hao Su +6
Speech signal analysis poses significant challenges, particularly in tasks such as speech quality evaluation and profiling, where the goal is to predict multiple perceptual and obj…