9 papers
Anchoring Speech with Semantics: A Multimodal Adapter Mechanism for Automatic Speech Recognition in Low-Resource Languages
Kuan-Tang Huang, Cheng-Yeh Yang, Chien-Chun Wang +3
Low-resource ASR remains difficult because scarce transcripts provide limited supervised evidence for target-side generation. To address this gap, we propose SAMA-ASR, a lightweigh…
Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification
Ming-Hsiang Hu, Kuan-Tang Huang, Chien-Chun Wang +2
User-defined keyword spotting (UD-KWS) enables zero-shot wake-word detection from text, but existing systems learn speaker-invariant representations that cannot reject impostors ut…
Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlations
Kuan-Tang Huang, Chien-Chun Wang, Cheng-Yeh Yang +3
The rapid proliferation of AI-Generated Content (AIGC) has necessitated robust metrics for perceptual quality assessment. However, automatic Mean Opinion Score (MOS) prediction mod…
Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing
An-Ci Peng, Kuan-Tang Huang, Tien-Hong Lo +3
Taiwanese Hakka is a low-resource, endangered language that poses significant challenges for automatic speech recognition (ASR), including high dialectal variability and the presen…
CLiFT-ASR: A Cross-Lingual Fine-Tuning Framework for Low-Resource Taiwanese Hokkien Speech Recognition
Hung-Yang Sung, Chien-Chun Wang, Kuan-Tang Huang +4
Automatic speech recognition (ASR) for low-resource languages such as Taiwanese Hokkien is difficult due to the scarcity of annotated data. However, direct fine-tuning on Han-chara…
Mitigating Data Imbalance in Automated Speaking Assessment
Fong-Chun Tsai, Kuan-Tang Huang, Bi-Cheng Yan +2
Automated Speaking Assessment (ASA) plays a crucial role in evaluating second-language (L2) learners proficiency. However, ASA models often suffer from class imbalance, leading to…
DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction
Cheng-Yeh Yang, Kuan-Tang Huang, Chien-Chun Wang +3
A pooling mechanism is essential for mean opinion score (MOS) prediction, facilitating the transformation of variable-length audio features into a concise fixed-size representation…
Revealing the Role of Audio Channels in ASR Performance Degradation
Kuan-Tang Huang, Li-Wei Chen, Hung-Shin Lee +2
Pre-trained automatic speech recognition (ASR) models have demonstrated strong performance on a variety of tasks. However, their performance can degrade substantially when the inpu…
QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems
Chien-Chun Wang, Kuan-Tang Huang, Cheng-Yeh Yang +3
Evaluating audio generation systems, including text-to-music (TTM), text-to-speech (TTS), and text-to-audio (TTA), remains challenging due to the subjective and multi-dimensional n…