10 papers
ParaAnya: Accelerating Parallel Diffusion Sampling with Plug-and-Play Output Caching
Chee-En Yu, Xiao-Xi Tan, Yi-Cheng Lin +3
Diffusion models have achieved remarkable success in generative tasks, but their inherently sequential sampling process introduces a severe computational bottleneck. Recent Paralle…
Toward Human-Aligned Judgement of Speech Emotion Similarity
Yun-Shao Tsai, Yi-Cheng Lin, Chih-Kai Yang +7
Evaluating emotion preservation in expressive speech generation involves assessing how closely generated speech matches a reference in emotion. Human listening tests assess this si…
Listen, Critique, and Refine: RL-Based Self-Refinement for Instruction-Following Speech Synthesis
Chee-En Yu, Yi-Cheng Lin, Sung-Feng Huang +4
Large Audio Language Models (LALMs) can follow diverse instructions to synthesize speech in specified styles. However, complex instructions that require simultaneous control over p…
Hearing Like Humans? Sound Symbolism and Perceptual Alignment in Speech Language Models
Yun-Shao Tsai, Chun-Wei Chen, Chee-En Yu +2
Sound symbolism, the human tendency to map speech sounds to perceptual qualities such as roundness or sharpness, arises primarily from the acoustics of speech rather than spelling.…
Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI
Yi-Cheng Lin, Yun-Shao Tsai, Kuan-Yu Chen +6
Speech technologies are deployed in high-stakes settings, yet fairness concerns remain fragmented across tasks and disciplines. Existing surveys either adopt a general machine-lear…
The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation
Yun-Shao Tsai, Yi-Cheng Lin, Huang-Cheng Chou +5
Objective metrics for emotional expressiveness are vital for speech generation, particularly in expressive synthesis and voice conversion requiring emotional prosody transfer. To q…
TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild
Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou +9
Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limited resources. In this paper, we intro…
MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
Chih-Kai Yang, Yun-Shao Tsai, Yu-Kai Guo +7
While multi-audio understanding is critical for large audio-language models (LALMs), it remains underexplored. We introduce MUGEN, a comprehensive benchmark evaluating this capabil…
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…
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
Chien-yu Huang, Wei-Chih Chen, Shu-wen Yang +77
Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spo…