Xianwei Zou

5000 Forbes Avenue

Pittsburgh, PA 15213

I am currently a Master student at Carnegie Mellon University, Electrical and Computer Engineering Deparment. I am interested in Machine Learning System in general, especially interested in Efficient Machine Leaning, recently interested in Parallel Computing, High Performance Computing and Scientific Machine Learning.

Fun Fact: see Personal

News

Jan 20, 2024	After six months of ‘marinating’ (a.k.a. procrastinating) the idea, I finally set up my personal website in just one hour, thanks to a nifty template I found.
May 17, 2023	My first paper as a co-first author, titled “The Hidden Dance of Phonemes and Visage: Unveiling the Enigmatic Link between Phonemes and Facial Features,” has been accepted at INTERSPEECH 2023.

Selected Publications

* indicates equal contribution

INTERSPEECH

The Hidden Dance of Phonemes and Visage: Unveiling the Enigmatic Link between Phonemes and Facial Features

Liao Qu* , Xianwei Zou* , Xiang Li* , and 3 more authors

In INTERSPEECH 2023 , Aug 2023

Abs arXiv HTML Code

This work unveils the enigmatic link between phonemes and facial features. Traditional studies on voice-face correlations typically involve using a long period of voice input, including generating face images from voices and reconstructing 3D face meshes from voices. However, in situations like voice-based crimes, the available voice evidence may be short and limited. Additionally, from a physiological perspective, each segment of speech – phoneme – corresponds to different types of airflow and movements in the face. Therefore, it is advantageous to discover the hidden link between phonemes and face attributes. In this paper, we propose an analysis pipeline to help us explore the voice-face relationship in a fine-grained manner, i.e., phonemes vs. facial anthropometric measurements (AM). We build an estimator for each phoneme-AM pair and evaluate the correlation through hypothesis testing. Our results indicate that AMs are more predictable from vowels compared to consonants, particularly with plosives. Additionally, we observe that if a specific AM exhibits more movement during phoneme pronunciation, it is more predictable. Our findings support those in physiology regarding correlation and lay the groundwork for future research on speech-face multimodal learning.