Tao Tu

(In search of a PhD position starting in 2024)

tao.png

ttaoretw@gmail.com


Tao Tu is currently a research assistant in the Department of Electrical Engineering at National Tsing Hua University, where he works with Prof. Min Sun. He is also a visiting researcher in UCMerced’s VLLab, working with Prof. Ming-Hsuan Yang. His aspiration is to empower machines with the intelligence to comprehend and engage with their surroundings. Currently, his primary areas of focus encompass 3D computer vision and multimodal learning.

Before joining NTHU, he was an algorithm engineer at MediaTek. Prior to that, in 2020, he gained valuable experience as an applied scientist intern with Amazon. He received a M.S. degree in Computer Science & Information Engineering from National Taiwan University and a B.S. degree in Electrical Engineering and Computer Science from National Tsing Hua University. He was a member of the Speech Processing Lab, working with Prof. Lin-shan Lee and Prof. Hung-yi Lee in the area of machine learning and speech processing.

News

Jul 14, 2023 ImGeoNet is accepted by ICCV’23. See you at Paris!
Apr 6, 2023 Join UCMerced’s VLLab as a Visiting Researcher (work with Prof. Ming-Hsuan Yang).
Oct 11, 2022 Join NTHU VSLab as a Research Assistant (work with Prof. Min Sun).
Feb 28, 2021 My work during Amazon internship READ-UP is accepted by CVPR’21.
Dec 7, 2020 Join MediaTek as an Algorithm Engineer.
Nov 1, 2020 Graduated from NTU. Grateful to Prof. Lin-shan Lee and Prof. Hung-yi Lee for their guidance.
Jul 25, 2020 Multi-speaker SeqRQ-AE is accepted by Interspeech’20.
Jul 13, 2020 Join Amazon as an Applied Scientist Intern.
Jan 24, 2020 SeqRQ-AE is accepted by ICASSP’20.
Jun 17, 2019 Cross-lingual Transfer Learning TTS is accepted by Interspeech’19.
Sep 1, 2018 Join NTU Speech Lab as a Graduate Student.

Experience

Apr, 2023 - Current Visiting Researcher @ UCMerced VLLab
Oct, 2022 - Current Research Assistent @ NTHU VSLab
Dec, 2020 - Oct, 2022 Algorithm Engineer @ MediaTek
Jul, 2020 - Oct, 2020 Applied Scientist Intern @ Amazon
Sep, 2018 - Nov, 2020 Graduate Student @ NTU CSIE
Sep, 2014 - Jun, 2018 Undergraduate Student @ NTHU EECS

Selected Publications

⭐ The preview images/videos are zoomable.

2023

  1. imgeonet.gif
    ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection
    Tao Tu, Shun-Po Chuang, Yu-Lun Liu, Cheng Sun, Ke Zhang, Donna Roy, Cheng-Hao Kuo, and Min Sun
    In ICCV, 2023
    Website Code (coming soon)

2021

  1. readup.png
    Learning better visual dialog agents with pretrained visual-linguistic representation
    Tao Tu, Qing Ping, Govindarajan Thattai, Gokhan Tur, and Prem Natarajan
    In CVPR, 2021
    Paper arXiv Code

2020

  1. semi-tts.png
    Semi-Supervised Learning for Multi-Speaker Text-to-Speech Synthesis Using Discrete Speech Representation
    Tao Tu, Yuan-Jui Chen, Alexander H Liu, and Hung-yi Lee
    Interspeech, 2020
    Paper arXiv Code Demo
  2. seqrq-ae.png
    Towards unsupervised speech recognition and synthesis with quantized speech representation learning
    Tao Tu (co-first), Alexander H Liu (co-first), Hung-yi Lee, and Lin-shan Lee
    In ICASSP, 2020
    Paper arXiv Video Demo

2019

  1. low-resrc-tts.png
    End-to-End Text-to-Speech for Low-Resource Languages by Cross-Lingual Transfer Learning
    Tao Tu (co-first), Yuan-Jui Chen (co-first), Cheng-chieh Yeh, and Hung-yi Lee
    Interspeech, 2019
    arXiv Demo