Publications

Preprints

• Takaaki Saeki, Shinnosuke Takamichi, and Hiroshi Saruwatari
  Incremental Text-to-Speech Synthesis Using Pseudo Lookahead with Large Pretrained Language Model
  arXiv:2012.12612 [cs.SD]
  [arXiv] [demo]

Journal Paper

• Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, and Hiroshi Saruwatari
  Real-Time Full-Band Voice Conversion with Sub-Band Modeling and Data-Driven Phase Estimation of Spectral Differentials
  IEICE Transactions on Information and Systems (ACCEPTED)

International Conference (Peer-Reviewed)

• Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, and Hiroshi Saruwatari
  Real-Time, Full-Band, Online DNN-Based Voice Conversion System Using a Single CPU
  Conference of the International Speech Communication Association (INTERSPEECH), 2020. (Show & Tell)
  [ISCA Archive] [video]
• Naoki Kimura, Zixiong Su, and Takaaki Saeki
  End-to-End Deep Learning Speech Recognition Model for Silent Speech Challenge
  Conference of the International Speech Communication Association (INTERSPEECH), 2020. (Show & Tell)
  [ISCA Archive] [video]
• Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, and Hiroshi Saruwatari
  Lifter Training and Sub-Band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.
  [IEEE Xplore] [arXiv] [slide] [video]

Domestic Conference (Non-Reviewed)

• Takaaki Saeki, Shinnosuke Takamichi, and Hiroshi Saruwatari
  End-to-End Incremental TTS Using Lookahead Generation with Large Pretrained Language Model
  IEICE Technical Report, 2021. (in Japanese)
  (IEICE ISS Student Poster Award)
  [paper]
• Masaki Kurata, Shinnosuke Takamichi, Takaaki Saeki, Riku Arakawa, Yuki Saito, Keita Higuchi, and Hiroshi Saruwatari
  Individuality Acquisition Method Using Auditory Feedback with DNN-Based Real-Time Voice Conversion System
  IPSJ SIG Technical Report, 2021. (in Japanese)
  [paper]
• Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, and Hiroshi Saruwatari
  Implementation and Evaluation of Real-Time Full-Band DNN-Based Voice Conversion Based on Sub-Band Filtering
  ASJ, Autumn Meeting, 2020. (in Japanese)
  [paper] [slide]
• Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, and Hiroshi Saruwatari
  Sub-Band Lifter-Training Method for Full-Band Voice Conversion Using Spectral Differentials
  ASJ, Spring Meeting, 2020. (in Japanese)
  [paper]
• Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, and Hiroshi Saruwatari
  Lifter Training and Sub-Band Modeling for DNN-Based Voice Conversion Using Spectral Differentials
  IPSJ SIG Technical Report, 2020. (in Japanese)
  [paper] [slide]
• Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, and Hiroshi Saruwatari
  Filter Estimation for Computational Complexity Reduction of DNN-based Voice Conversion Using Spectral Differentials
  ASJ Autumn Meeting, 2019. (in Japanese)
  [paper]

Thesis

• Takaaki Saeki (Supervisor: Prof. Hiroshi Saruwatari)
  Real-Time, Full-Band, High-Quality Neural Voice Conversion with Sub-Band Modeling and Data-Driven Phase Estimation
  Master’s Thesis, Graduate School of Information Science and Technology, the University of Tokyo, 2021.
  [thesis] [slide]