Yusuke Yasuda

Biography

Yusuke Yasuda received his BS and MS degrees at Waseda University, Japan, in 2012 and 2014, respectively. He received his Ph.D degree from the Graduate University for Advanced Studies, SOKENDAI, Japan, in 2021. He was a research assistant at the National Institute of Informatics, Japan, from 2018 to 2021. From 2021 to 2025, he was a project lecturer at Nagoya University, Japan. Since 2025, he has been a project assistant professor at the National Institute of Informatics, Japan. He received the second Yoshida Award from the Acoustical Society of Japan in 2023. His research interests include machine learning, speech synthesis, and speech evaluation.

Career

Awards

• 2015 AWS IoT Hackathon AWS Award, DMM.make Award
• 2020 Acoustical Society of Japan 20th Student Outstanding Presentation Award
• 2023 Acoustical Society of Japan 2nd Yoshida Award for Speech Synthesis Research Encouragement
• 2023 ASRU 2023 Best Reviewer Award

Academic Activities

• Member of IEEE, ISCA, and the Acoustical Society of Japan

Recent Research

• [Domestic Conference] Expert-independent accent annotation method using accent-controlled speech synthesis and subjective comparative evaluation optimization
• Continual Subjective Evaluation Method of Speech by Merging Sort-based Preference Tests Towards Ever-Expanding Corpus of Human Ratings
• Hot topics in speech synthesis evaluation
• How Similar or Different Is Rakugo Speech Synthesizer to Professional Performers?
• End-to-End Text-to-Speech using Latent Duration based on VQ-VAE
• Lexical Pitch Accent and Duration Modeling for Neural End-to-End Text-to-Speech Synthesis
• Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis
• [Arxiv] Pretraining Strategies, Waveform Model Choice, and Acoustic Configurations for Multi-Speaker End-to-End Speech Synthesis
• Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?
• [Domestic conference] How close can Rakugo speech synthesis come to the performance of a human Rakugo performer?
• Modeling of Rakugo Speech and Its Limitations: Toward Speech Synthesis That Entertains Audiences
• Effect of choice of probability distribution, randomness, and search methods for alignment modeling in sequence-to-sequence text-to-speech synthesis using hard alignment
• Initial investigation of encoder-decoder end-to-end TTS using marginalization of monotonic hard alignments
• [Domestic Conference] Robust Training Method for Rakugo Speech Synthesis Model and Dealing with Variations in Speaking Style
• [Domestic Conference] Initial Study on End-to-End Speech Synthesis without Soft Attention
• Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language
• [Domestic Conference] Use of Tacotron and Context Features in Rakugo Speech Synthesis and Its Evaluation
• [Domestic Conference] Rakugo Speech Synthesis Using WaveNet and Context Analysis - Toward Entertaining Speech Synthesis -
• [Domestic Conference] Towards Japanese End-to-End Speech Synthesis - Initial Study of Japanese Tacotron