Katsuhiko Yamamoto

• [NEW] Our demo & challenge paper has been accepted to ASRU 2025. 

• [NEW] Our paper has been accepted to INTERSPEECH 2025. 

• My affiliation was changed to AI Lab, CyberAgent, Inc.   

• GammachirPy: A Python package of the dynamic compressive gammachirp filterbank (Irino & Patterson, 2006) is available on my GitHub page.

Affiliation

• AI Lab, CyberAgent, Inc.

E-mail

yamamoto_katsuhiko(at)cyberagent.co.jp

Social Accounts

• X (Formerly Twitter) 

• Bluesky

• Mastodon 

• GitHub

• LinkedIn

• Google Scholar 

• Researchgate

• ORCID

Job Experiences

• 2023-Current Research Scientist at AI Lab, CyberAgent, Inc., Japan.

• 2019-2022 Engineer at Toyota Motor Corporation, Japan

• 2017-2019 Research Fellow of Young Scientist at Japan Society for the Promotion of Science (JSPS), Japan

Educational Backgrounds

• 2015-2019 Graduate School of System Engineering, Wakayama University, Japan

• 2013-2015 Graduate School of Information Science, Japan Advanced Institute of Science and Technology, Japan

• 2011-2013 Advanced course, Kobe city College of Technology, Japan

• 2006-2011 Associate course, Kobe city College of Technology, Japan

Research Topics

• Speech Intelligibility Prediction Based on Auditory Computational Models (Ph.D. Research Theme)

• Perceptional characteristics of bone-conducted sound (Master's Research Theme)

• Semi-scrambling method for speech signals based on phonemic restoration (Master's Research Sub-theme)

• Measuring the intelligibility of bone-conducted ultrasonic hearing aid in noisy environments  (Undergraduate Research Theme

Published Papers

•  K. Yamamoto, T. Irino, S. Araki, K. Kinoshita, and T. Nakatani, "GEDI: Gammachirp envelope distortion index for predicting intelligibility of enhanced speech,'' Speech Communication, Vol. 123, pp. 43-58, 2020. [Paper] [Software ]

• K. Yamamoto, T. Irino, S. Araki, K. Kinoshita, and T. Nakatani, “Speech intelligibility prediction using a multi-resolution gammachirp envelope distortion index with common parameters for different noise conditions, ” Acoustical Letter, Acoustical Society of Japan, Vol. 41, Issue 1, pp. 396-399. [Paper] 

• K. Yamamoto, T. Irino, T. Matsui, S. Araki, K. Kinoshita, and T. Nakatani, “Speech intelligibility prediction with the dynamic compressive gammachirp filterbank and modulation power spectrum,” Acoustical Science and Technology, Vol. 40, No. 2, pp. 84-92, March 2019. [Paper]

• K. Yamamoto, Z. Zhu, M. Unoki and N. Aoki, "Study on Semi-Scramble Method for Speech Signals Based on Phonemic Restoration," Journal of Signal Processing, Research Institute of Signal Processing Japan, Vol.18, No.4 Special Issue on Papers Awarded the Student Paper Award at NCSP'14, pp. 205-208, July 2014. [Paper]

• Z. Zhu, K. Yamamoto, M. Unoki and N. Aoki, "Study on Scramble Method for Speech Signal by Using Random-Bit Shift of Quantization," Journal of Signal Processing, Research Institute of Signal Processing Japan, Vol.18, No.6  Special Issue on Nonlinear Circuits, Communications and Signal Processing, pp. 303-307, November 2014. [Paper]

Conference Activities & Talks

(International)

• [New] K. Yamamoto and K. Miyazaki (2025) "Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners," in Proc. Interspeech 2025, 5463-5467, doi: 10.21437/Interspeech.2025-1377. [Paper]

• K. Arai, S. Araki, A. Ogawa, K. Kinoshita, T. Nakatani, K. Yamamoto, and T. Irino (2019) "Predicting Speech Intelligibility of Enhanced Speech Using Phone Accuracy of DNN-based ASR Systems," in Proc. Interspeech 2019, pp. 4275 - 4279. [Paper]

• Yamamoto, K., Irino, T., Araki, S., Kinoshita, K., Nakatani, T. (2018) "Speech intelligibility prediction using a multi-resolution gammachirp envelope distortion index with common parameters for different noise conditions." in Proc. Seminar on brain, hearing and speech sciences for universal speech communication/Universal Symposium on Universal Acoustical Communication 2018 (UAC2018), October 2018. 

• Yamamoto, K., Irino, T., Ohashi, N., Araki, S., Kinoshita, K., Nakatani, T. (2018) "Multi-resolution Gammachirp Envelope Distortion Index for Intelligibility Prediction of Noisy Speech." in Proc. Interspeech 2018, 1863-1867.  [Paper] [Software ]

• Yamamoto, K., Irino, T., Matsui, T., Araki, S., Kinoshita, K., Nakatani, T. (2017) "Predicting Speech Intelligibility Using a Gammachirp Envelope Distortion Index Based on the Signal-to-Distortion Ratio." in Proc. Interspeech 2017, pp. 2949 - 2953, DOI: 10.21437/Interspeech.2017-170. [Paper] [Software ]

• K. Yamamoto, T. Irino, T. Matsui, S. Araki, K. Kinoshita and T. Nakatani (2016), “Analysis of acoustic features for speech intelligibility prediction models,” in Proceedings of 5th Joint Meeting of the ASA/ASJ, Journal of the Acoustical Society America, Vol. 140, No. 4, Pt. 2, p. 3114, October 2016.

• Yamamoto, K., Irino, T., Matsui, T., Araki, S., Kinoshita, K., Nakatani, T. (2016) Speech Intelligibility Prediction Based on the Envelope Power Spectrum Model with the Dynamic Compressive Gammachirp Auditory Filterbank. Proc. Interspeech 2016, 2885 - 2889. [Paper]

• K. Yamamoto, T. Irino, T. Matsui, S. Araki, K. Kinoshita and T. Nakatani (2014), “Study on predicting speech intelligibility of enhanced speech sounds using the dynamic compressive gammachirp auditory filterbank and modulation filterbank,” presented at Taiwan/Japan Joint Auditory Research Meeting, National Tsing Hua University, Taiwan, 23–24 October 2015.

• Yamamoto, K., Zhu, Z., Unoki, M. and Aoki, N. (2014), "Study on Semi-Scramble Method for Speech Signals Based on Phonemic Restoration," 2014 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing, 1PM2-2-1, pp. 201-204, Honolulu, Hawaii, USA, 1-3, March 2014, [Student Paper Award]

• Zhu, Z., Yamamoto, K., Unoki and M., Aoki, N. (2014), "Study on scramble method for speech signal by using random-bit shift of quantization," 2014 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing, 1PM1-2-2, pp. 109-102, Honolulu, Hawaii, USA, 1-3, March 2014.

Software

• [New] GammaChirPy: A python package of the dynamic compressive gammachirp filterbank (Irino & Patterson, 2006) [Python] 

• Gammachirp Envelope Distortion Index (GEDI): An objective speech intelligibility metric based on human auditory models (Yamamoto et al., 2020) [MATLAB]

Awards

• President’s Award, Wakayama University, 2017.

• Dean’s Award, Graduate School of Systems Engineering, Wakayama University, 2016.

• First Prize of Best Presentation Award, The 18 th Young Researchers Meeting, Kansai Branch of Acoustical Society of Japan, 2015.

• Student Presentation Award,2015 Spring Meeting of the Acoustical Society of Japan, Acoustical Society of Japan, 2015.

• Student Paper Award, NCSP'14, Research Institute of Signal Processing, 2014.

• Student Presentation Award, The JHES 2013, Hokuriku Branch of Acoustical Society of Japan, 2013.

• Second Prize of Best Presentation Award and Special Award, The 15th Young Researchers Meeting, Kansai Branch of Acoustical Society of Japan, 2012.