About

I am a 2nd-year Master student at Saruwatari & Saito Lab., Graduate school of Information Science and Technology, the University of Tokyo, Japan. My research focuses on the domain of speech and language processing such as speech synthesis, voice conversion, and para/non-linguistic information modeling. I am especially interested in modeling and generating expressive prosody. Also, through it, I aim to the development of human-friendly speech agents that can adaptively and naturally communicate with a variety of people.

東京大学 大学院情報理工学系研究科 猿渡・齋藤研究室 修士2年の山内一輝です． 音声合成，音声変換，パラ言語/非言語情報のモデリングなど，音声言語情報処理の領域を中心に研究しています． その中でも特に，表現力豊かな韻律のモデリングや生成に興味を持っています． また，それを通して，様々な人と適応的かつ自然にコミュニケーションができる，ヒューマンフレンドリーな音声エージェントの開発を目指しています．

Email (university): yamauchi-kazuki042 [at] g.ecc.u-tokyo.ac.jp
Email (personal): kyamauchi1023 [at] gmail.com
Address: Room #140, Engineering bldg. #6, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

Research Interests

• Speech and Language Processing
• Speech Synthesis
• Natural Language Processing
• Deep Learning
• Signal Processing

Education

• Apr. 2023 - Present
  Master’s Degree in Information Science and Technology, the University of Tokyo, Japan
  Department of Creative Informatics, Graduate School of Information Science and Technology
  (東京大学 大学院情報理工学系研究科 創造情報学専攻)
• Apr. 2019 - Mar. 2023
  Bachelor’s Degree in Engineering, the University of Tokyo, Japan
  Department of Mathematical Engineering and Information Physics, Faculty of Engineering
  (東京大学 工学部 計数工学科)
• Apr. 2016 - Mar. 2019
  Aichi Prefectural Meiwa Senior High School
  (愛知県立明和高等学校)

Awards & Honours

• Jun. 2024
  🎉 Best Presentation Award / 優秀発表賞 [link]
  Sound Symposium / 音学シンポジウム
• Mar. 2024
  🎉 Ranked 1st in TTS (Acoustic+Vocoder) track [link]
  Interspeech2024 Speech Processing Using Discrete Speech Unit Challenge
• Mar. 2024
  🎉 Best Student Presentation Award / 学生優秀発表賞 [link]
  Acoustical Society of Japan, ASJ / 日本音響学会
• Mar. 2024
  🎉 Best Student Poster Award / 学生ポスター賞 [link]
  IEICE Speech Committee / 電子情報通信学会 音声研究会

Research and Work Experiences

• Mar. 2023 - Present
  CoeFont Co.,Ltd. / 株式会社CoeFont, Part-Time AI Researcher
  Researching on speech processing.
• Jul. 2024 - Sep. 2024
  RIKEN Guardian Robot Project / 理研ガーディアンロボットプロジェクト, Research Internship
  Researched at Knowledge Acquisition and Dialogue Research Team.
• Aug. 2023 - Sep. 2023
  NTT Human Informatics Laboratories / NTT人間情報研究所, Research Internship
  Researched on speaking style captioning.
• Sep. 2021 - Mar. 2024
  Nagase Brothers Inc. / 株式会社ナガセ, Part-Time AI Researcher & Engineer
  Worked on natural language processing and developed web application.

Volunteer Works:

• Oct. 2024 - Present
  Acoustical Society of Japan (ASJ) Students and Young Researchers Forum, member / 日本音響学会 学生・若手フォーラム 幹事会員

Misc.

• Apr. 2024
  Invited to Google Research Talk, Google Tokyo, Japan
  Talked about our technical report for Interspeech2024 Speech Processing Using Discrete Speech Unit Challenge.