Member Highlight: Dr. Shoko Araki

Member Highlight: Dr. Shoko Araki
Senior Research Scientist, NTT Communication Science Laboratories
NTT Corporation, Japan

Dr. Shoko Araki is a Senior Research Scientist at NTT Communication Science Laboratories, NTT Corporation, Japan, where she is currently leading the Signal Processing Research Group. Since she joined NTT in 2000, she has been engaged in research on acoustic signal processing, array signal processing, blind source separation, meeting diarization, and auditory scene analysis. She received the B.E. and M.E. degrees from the University of Tokyo, Japan, in 1998 and 2000, respectively, and the Ph.D. degree from Hokkaido University, Japan, in 2007.

She was formerly a member of the IEEE SPS Audio and Acoustic Signal Processing Technical Committee (AASP-TC) (2014–2019), its vice-chair (2022), chair (2023–2024), and currently serves as its past chair (2025). She was a board member of the Acoustical Society of Japan (ASJ) (2017–2021) and served as its vice president (2021–2023). 

She has authored and co-authored around 50 peer-reviewed papers in academic journals and more than 200 peer-reviewed international conference papers. She has been awarded various international and domestic awards, including the IEEE SPS Best paper award in 2014, the IEEE ASRU 2015 Best Paper Award Honorable Mention in 2015, and the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology, The Young Scientists' Prize in 2014. She was elevated to an IEEE Fellow in 2022 for contributions to blind source separation of noisy and reverberant speech signals.

We approached Dr. Shoko Araki to learn more:

Q: Why did you choose the industry in signal processing?

Having been fond of playing musical instruments since I was a child, I was interested in sound, music, and human hearing, and I wanted to work in those fields. NTT had many pioneers in these disciplines, so I joined the company with the hope of working with them. I feel very fortunate to now be working with them in R&D related to audio and speech processing.

Q: How does your work affect society?

I would feel honored if my accomplishments had contributed even a little to opening up a new interdisciplinary research field, blind audio source separation.

My work revealed the relationship between independent component analysis (ICA)-based blind source separation (BSS) and the most fundamental microphone array signal processing technique, i.e., acoustic adaptive beamforming. I also pioneered the approach of combining time-frequency mask-based BSS and beamforming techniques for accurate speech enhancement.

These findings provided new and powerful tools for well-established microphone array signal processing techniques, and they helped to improve BSS performance in real reverberant environments. Blind audio source separation gained momentum in the first two decades of the 21st century, and currently, it has grown into one of the most important topics in the Signal Processing Society AASP area: we can find many sessions on BSS of audio/speech/music signals at many international conferences.

Q: What challenges have you had to face to get to where you are today?

In Japan, unfortunately, women remain in the minority among those pursuing careers in science and engineering, and they often face challenging issues; this situation was even worse when I was younger.

When I was in high school and had to choose between the humanities and the sciences, I wanted to study science. However, my teachers opposed this wish of mine, so I had to convince them. Having a clear idea of ​​what I wanted to do and continuing to clearly explain it to the people around me paid off. It is important to stubbornly hold a dream but also respond to reality flexibly. Fortunately, thanks to the understanding and support of my supervisors, colleagues, parents and others, I did not encounter any major obstacle after I started to study engineering in my second year of university.

Another challenge would be English. This is a common and never-ending challenge for non-native speakers, and we need to keep studying!

Q: What advice would you give to scientists/engineers in signal processing?

Evaluate your technologies with realistic signals, not just simulations. Theoretical studies, simulations, and studies using common datasets/corpora are all important. In addition, I think it is important to always evaluate technologies using real signal data. I am an acoustic researcher, and I always prefer to carry out evaluations using my own recorded data and/or building a PoC (proof-of-concept) system if the situation allows. This approach is not only effective for checking the feasibility of a given technology, but it also often leads to the discovery of (sometimes unexpected) new research problems.

Q: Is there anything else that you would like to add?

In particular, to young people: Have a commitment to what you would like to do, but be flexible, and make your way. This attitude is equally beneficial when considering your career path and when considering your R&D policy. Be clear about your commitment and explain it to those around you. The people around you will probably give you a variety of opinions, both positive and negative, but they are all valuable suggestions: all of them are aimed at helping you, your department, and your company. I believe that if you are flexible based on your own commitment and the voices of those around you, you will be able to blaze a great trail.

Finally, I would like to thank everyone who named me for the “Member Highlights”, and everyone who has supported me throughout my career.