Yayue Deng

School of Artificial Intelligence, Beijing University of Posts and Telecommunications

prof_pic.jpg

(+86)18810956816

yayue.deng@bupt.edu.cn

No.10 Xitucheng Road, Haidian District, Beijing, China 100876

Hello! My name is Yayue Deng. I am a dedicated Artificial Intelligence Master’s student at Beijing University of Posts and Telecommunications (BUPT), with an expected graduation date in June 2025.

My academic focus is on Artificial Intelligence and Machine Learning, with a particular interest in Speech Synthesis and Natural Language Processing. My ultimate goal is to leverage my expertise in these areas to develop a conversational chatbot that exhibits both emotional and intellectual intelligence. I am currently researching Speech Synthesis (TTS) and Spoken Dialogue Systems as part of my Master’s degree, which aligns with my future aspirations.

You can also read more about my research experience and my background by clicking or google scholar.

My future plan is to pursue a doctoral degree. If you are interested in my field of research, please feel free to contact me at yayue.deng@bupt.edu.cn or Twitter!


news

Feb 1, 2024 Obtain the National Scholarship (国家奖学金).
Jan 29, 2024 Gave a talk at ICASSP 2024 Pre-Conference Seminar (语音之家 “ICASSP 2024论文预讲会”) on Conversational Speech Synthesis! [Link] [slide].
Jan 29, 2024 Received the IEEE SPS Scholarship from the IEEE Signal Processing Society. :laughing:
Dec 14, 2023 My paper “CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis” Accepted by ICASSP 2024.:raised_hands:
Jun 19, 2023 Passing Test for English Majors-Band 8(TEM-8)
Sep 1, 2022 Qualified for the recommendation for postgraduate study, joined Professor Li Ya’s research group, and started the postgraduate stage.:sparkles: :smile:
Nov 8, 2021 I stayed a six-month internship at the Artificial Intelligence Department of China Mobile Research Institute.
Aug 1, 2021 Starting the study of the ‘Prospect Talents in Digital Economy’ program at Guanghua School of Management, Peking University.


selected publications

2023

  1. CONCSS.jpg
    CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis
    Yayue Deng, Jinlong Xue, Yukang Jia, and 6 more authors
    arXiv preprint arXiv:2312.10358, 2023
  2. cmcu.png
    CMCU-CSS: Enhancing Naturalness via Commonsense-based Multi-modal Context Understanding in Conversational Speech Synthesis
    Yayue Deng, Jinlong Xue, Fengping Wang, and 2 more authors
    In Proceedings of the 31st ACM International Conference on Multimedia, 2023
  3. icassp2023.png
    M2-CTTS: End-to-End Multi-Scale Multi-Modal Conversational Text-to-Speech Synthesis
    Jinlong Xue, Yayue Deng, Fengping Wang, and 5 more authors
    In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

2022

  1. RC-Attention.png
    Rhythm-controllable Attention with High Robustness for Long Sentence Speech Synthesis
    Dengfeng Ke, Yayue Deng, Yukang Jia, and 6 more authors
    In 2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2022


Experience

07/2020 - 04/2021

Three-dimensional Human-computer Interaction Model Design for Chinese Pronunciation

Act as an excellent project leader of National College Students’ Innovation and Entrepreneurship Training Program. The project is used to help the Chinese learners understand the exact location and method of the phoneme articulation intuitively. This project introduced a dynamic three dimensional (3D) head model built based on the knowledge of anatomy and the theory of distinctive features.

paper

04/2021 - 09/2021

Detecting Moral Sentiment In Text

Expressions of moral sentiment play a fundamental role in political framing, social solidarity, and basic human motivation. This research aims at detecting and understanding the moral biases in text.

paper

09/2021 - 12/2022

Expressive Speech Synthesis Research

My research on expressiveness text-to-speech aims to synthesize intelligible and natural speech,which focuses on prosody, emotion, and style modeling.

paper

11/2021 - 06/2022

Fake Speech Generation

Participated in the First Audio Deep Synthesis Detection Challenge (ADD 2022) in ICASSP 2022, responsible for utilizing non-autoregressive speech synthesis system to generate fake speech As Winter intern in China Mobile Research Institute,Beijing, Artificial Intelligence Department

official website

09/2022 - 12/2023

Conversational Speech Synthesis

Participated in the “interactive and empathetic spoken speech generation for mental health counseling” project , which is supported by Open Project Program of the National Laboratory of Pattern Recognition (NLPR).

paper

Granted four invention patents abd approved for a project by the National Natural Science Foundation of China

paper