11 citations · 55 across the 50 of their papers we have counts for
19 papers · 1 filter
Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition
Yi-Cheng Lin, Yu-Hsuan Li Liang, Hsuan Su +4
Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical work…
TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics
Yi-Cheng Lin, Yu-Hua Chen, Jia-Kai Dong +12
Large audio-language models are advancing rapidly, yet most evaluations emphasize speech or globally sourced sounds, overlooking culturally distinctive cues. This gap raises a crit…
MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
Hsiao-Ying Huang, Yi-Cheng Lin, Hung-yi Lee
Large audio-language models (LALMs) show strong zero-shot ability on speech tasks, suggesting promise for speech emotion recognition (SER). However, SER in real-world deployments o…
How Does Instrumental Music Help SingFake Detection?
Xuanjun Chen, Chia-Yu Hu, I-Ming Lin +8
Although many models exist to detect singing voice deepfakes (SingFake), how these models operate, particularly with instrumental accompaniment, is unclear. We investigate how inst…
Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems
Yi-Cheng Lin, Huang-Cheng Chou, Tzu-Chieh Wei +2
Instruction-guided text-to-speech (ITTS) enables users to control speech generation through natural language prompts, offering a more intuitive interface than traditional TTS. Howe…
ASTAR-NTU solution to AudioMOS Challenge 2025 Track1
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jui-Chiang Wei +3
Evaluation of text-to-music systems is constrained by the cost and availability of collecting experts for assessment. AudioMOS 2025 Challenge track 1 is created to automatically pr…
MMMOS: Multi-domain Multi-axis Audio Quality Assessment
Yi-Cheng Lin, Jia-Hung Chen, Hung-yi Lee
Accurate audio quality estimation is essential for developing and evaluating audio generation, retrieval, and enhancement systems. Existing non-intrusive assessment models predict…
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu +25
We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following. Recent LALMs augment Large Langu…
HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment
Wenze Ren, Yi-Cheng Lin, Wen-Chin Huang +9
Modern speech quality prediction models are trained on audio data resampled to a specific sampling rate. When faced with higher-rate audio at test time, these models can produce bi…
A correlation-permutation approach for speech-music encoders model merging
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jeremy H. M Wong +3
Creating a unified speech and music model requires expensive pre-training. Model merging can instead create an unified audio model with minimal computational expense. However, dire…
Multi-Distillation from Speech and Music Representation Models
Jui-Chiang Wei, Yi-Cheng Lin, Fabian Ritter-Gutierrez +1
Real-world audio often mixes speech and music, yet models typically handle only one domain. This paper introduces a multi-teacher distillation framework that unifies speech and mus…
EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition
Yi-Cheng Lin, Huang-Cheng Chou, Yu-Hsuan Li Liang +1
Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain und…
CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition
Yun-Shao Tsai, Yi-Cheng Lin, Huang-Cheng Chou +1
Bias in speech emotion recognition (SER) systems often stems from spurious correlations between speaker characteristics and emotional labels, leading to unfair predictions across d…
Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach
Yi-Cheng Lin, Huang-Cheng Chou, Hung-yi Lee
While subgroup disparities and performance bias are increasingly studied in computational research, fairness in categorical Speech Emotion Recognition (SER) remains underexplored.…
Creativity in LLM-based Multi-Agent Systems: A Survey
Yi-Cheng Lin, Kang-Chieh Chen, Zhe-Yan Li +5
Large language model (LLM)-driven multi-agent systems (MAS) are transforming how humans and AIs collaboratively generate ideas and artifacts. While existing surveys provide compreh…
Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning
Liang-Yeh Shen, Shi-Xin Fang, Yi-Cheng Lin +2
This paper introduces Meta-PerSER, a novel meta-learning framework that personalizes Speech Emotion Recognition (SER) by adapting to each listener's unique way of interpreting emot…
ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality
Yu-Xiang Luo, Yi-Cheng Lin, Ming-To Chuang +9
Despite extensive research on toxic speech detection in text, a critical gap remains in handling spoken Mandarin audio. The lack of annotated datasets that capture the unique proso…
Distilling a speech and music encoder with task arithmetic
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jui-Chiang Wei +4
Despite the progress in self-supervised learning (SSL) for speech and music, existing models treat these domains separately, limiting their capacity for unified audio understanding…
BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights
Chan-Jan Hsu, Yi-Cheng Lin, Chia-Chun Lin +10
We present BreezyVoice, a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities to address the unique challenges of polyp…