Summary

Professor TOKUDA Keiichi (NITech Computer Science Group) received the 2024 IEEE James L. Flanagan Speech and Audio Processing Award. This is in recognition of Professor TOKUDA's pioneering contributions to statistical speech synthesis and speech signal processing over many years. The award ceremony took place at the 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024), held in Seoul, South Korea, from April 14 through 19, 2024.

The IEEE Technical Field Awards (TFAs) are the highest honors in the academic fields of science and technology associated with the IEEE, the world's largest society for electrical and information engineering. The IEEE James L. Flanagan Speech and Audio Processing Award is awarded to researchers and engineers who have made outstanding achievements in the field of speech and audio processing technology. IEEE Technical Field Awards have been bestowed on several Japanese researchers of international renown, including Nobel laureates such as Leo Esaki, Isamu Akasaki, and Shuji Nakamura. Well-known Japanese Nobel Prize winners, including ESAKI Leona, AKASAKI Isamu, and NAKAMURA Shuji, have received the IEEE Technical Field Award.

Research background, content, and outcomes

Speech synthesis basically involves generating spoken language from arbitrary text. In the 1990s, the principal method of was to connect recorded speech waveforms for each character in the text. However, Professor TOKUDA proposed a revolutionary approach to speech generation through "learning," using statistical generative models. His method demonstrated that it is possible to freely generate various voice qualities, speaking styles, and emotional expressions. Furthermore, by introducing the new concept of speech generation based on statistical models, Professor TOKUDA brought about a paradigm shift in the entire field of speech synthesis, establishing it as a new research area and greatly contributing to the advancement of other related fields. Professor TOKUDA's groundbreaking approach has since become a foundational method for most contemporary speech synthesis technologies. It also constitutes a driving force for cutting-edge neural network approaches in the context of generative AI, commonly referred to as AI speech synthesis.

Social impact

Professor TOKUDA's approach has directly or indirectly influenced most of the speech synthesis systems that are used daily by many people today, including voice assistants such as Alexa* and Siri* and car navigation systems. Moreover, speech synthesis technology is widely applied in accessibility tools such as screen readers for the visually impaired, language learning tools, voice reconstruction for people who have lost their voice due to conditions such as ALS or laryngeal cancer, PA systems, emergency broadcasting during disasters, speech translation apps, and singing voice synthesis software.

Professor TOKUDA has received numerous accolades for his achievements relating to speech signal processing technology. They include the Medal with Purple Ribbon, the Minister of Education, Culture, Sports, Science and Technology (MEXT) Award for Science and Technology, the ISCA Medal for Scientific Achievement, the Achievement Award of the Institute of Electronics, Information and Communication Engineers (IEICE), and the Kiyasu Special Industrial Achievement Award of the Information Processing Society of Japan (IPSJ). He has also received several awards for his papers from the IEEE and IEICE. Professor TOKUDA holds the titles of IEEE Fellow and ISCA Fellow.

IEEE James L. Flanagan Speech and Audio Processing Award - IEEE Awards