Chun-Yi Kuan
Hello! I’m Chun-Yi, a first-year Ph.D student at NTU Speech Processing and Machine Learning (SPML) Lab, supervised by Prof. Hung-yi Lee.
My research focuses on multi-modality large language models, exploring how to establish robust audio-language alignment to address recent trustworthiness issues, such as hallucination phenomena related to sound events in audio. I’m also involved in the Dynamic-SUPERB project phase 1 and 2, which benchmarks the performance of large audio-language models across universal speech, audio, and music tasks.
My previous research centered on text-guided speech generation tasks, investigating how to use textual information to guide the generation of high-quality speech with desired styles and prosody.
news
| May 28, 2025 | Our paper, “Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples”, has been accepted to Interspeech 2025 🇳🇱. |
|---|---|
| Jul 16, 2024 | 🚀 Excited to share our real-world application of using LLMs as automatic assignment evaluators in our Intro to Generative AI course at NTU with over 1000 students! Led by Prof. Hung-yi Lee and with tremendous contributions from Cheng-Han Chiang as the head TA. His dedication was crucial to the success of this work. Check out our findings and insights here: https://arxiv.org/abs/2407.05216 |
| Apr 15, 2024 | Excited to share 🔱 Speech Trident- Awesome Speech LM |