12 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…
DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment
Chien-Chun Wang, Hung-Shin Lee, Hsin-Min Wang +1
Evaluating text-to-music (TTM) systems remains expensive because music impression (MI) and text alignment (TA) scores rely on human mean opinion scores (MOS). Most automatic MOS es…
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…
Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancement
Chien-Chun Wang, Hung-Shin Lee, Hsin-Min Wang +1
Pre-trained models for automatic speech recognition (ASR) and speech enhancement (SE) have exhibited remarkable capabilities under matched noise and channel conditions. However, th…
TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition
Cheng-Yeh Yang, Chien-Chun Wang, Li-Wei Chen +3
Low-resource automatic speech recognition (ASR) continues to pose significant challenges, primarily due to the limited availability of transcribed data for numerous languages. Whil…
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…
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…
SincQDR-VAD: A Noise-Robust Voice Activity Detection Framework Leveraging Learnable Filters and Ranking-Aware Optimization
Chien-Chun Wang, En-Lun Yu, Jeih-Weih Hung +2
Voice activity detection (VAD) is essential for speech-driven applications, but remains far from perfect in noisy and resource-limited environments. Existing methods often lack rob…
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…
Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation
Chien-Chun Wang, Li-Wei Chen, Hung-Shin Lee +2
Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch…
Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition
Chien-Chun Wang, Li-Wei Chen, Cheng-Kang Chou +3
While pre-trained automatic speech recognition (ASR) systems demonstrate impressive performance on matched domains, their performance often degrades when confronted with channel mi…