Hi, I'm Candy! I am an assistant professor at School of Information Science, Japan Advanced Institute of Science and Technology (JAIST). My primary research interests are speech signal processing, machine learning, and social signal processing (SSP). My Ph.D. thesis focuses on privacy preservation and secure speech communication. In addition to primary research, I also carried out a research project on personality traits and communication skills modeling with Prof. Shogo Okada. I obtained my Ph.D. and M.S. degrees in Information Science, JAIST, advised by Prof. Masashi Unoki.
Research interests: speech information hiding, voice privacy, social signal processing, and machine learning.
News
A press release has been issued announcing our paper accepted in Computers and Education: Artificial Intelligence.
Our paper Robust Multilingual Audio Deepfake Detection Through Hybrid Modeling has been accepted for publication in the 13th ACM Workshop on Information Hiding and Multimedia Security.
To kick off the new academic year and welcome our new members, we held a welcome party! This gathering brought together students I directly supervise for their minor research, those I primarily co-advise on their master's theses, and collaborators from various ongoing projects.
Our paper InaSAS: Benchmarking Indonesian Speech Anti-Spoofing Systems has been accepted for publication in APSIPA Transactions on Signal and Information Processing.
Our paper Fine-tuning TitaNet-Large Model for Speaker Anonymization Attacker Systems has been presented at the 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025), Hyderabad, India.
The new fiscal year 2025 has begun. This year, I will be teaching course I225E Statistical Signal Processing with Professor Unoki in Term 1-1 (April-June). Wishing you all a productive year ahead!
I participated in the 2025 Spring meeting of the Acoustical Society of Japan (ASJ), Saitama University, Japan. Three of our reserach papers were presented in poster sessions.
Our paper Beyond Accuracy: Multimodal Modeling of Structured Speaking Skill Indices in Young Adolescents has been accepted for publication in Journal of Computers & Education: Artificial Intelligence.
I receive the JSPS Kakenhi for Early-Career Scientists FY2025 (科研費 若手研究)).
Mr. Hiroto Horimoto and Mr. Shinya Koshikawa, master students from Okada laboratory, finished their final defense. お疲れ様でした!
Mr. Wenqing Wei and Mr. Fuminori Nagasawa, Ph.D candidates from Okada laboratory, finished their final defense. お疲れ様でした!
Our paper Influence of Personality Traits and Demographics on Rapport Recognition Using Adversarial Learning has been accepted for publication in Multimodal Technologies and Interaction.
Our paper Speech Intelligibility Prediction Using Binaural Processing for Hearing Loss has been accepted for publication in IEEE Access.
Our paper WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines has been accepted for presentation at the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025), Albuquerque, New Mexico. Deep appreciation to all co-authors for their dedication to the success of this big project.
Our paper Indonesian Speech Content De-Identification in Low Resource Transcripts has been presented by our student, Mr. Rifqi Naufal Abdjul, at The Second Workshop in South East Asian Language Processing (SEALP 2025), Co-loacted with (COLING 2025), Abu Dhabi (Online).
Our paper Fine-tuning TitaNet-Large Model for Speaker Anonymization Attacker Systems has been accepted for presentation at the 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025) - Grand Challenge (The First VoicePrivacy Attacker Challenge), Hyderabad, India.
Cheers to a year of new adventures, fresh starts, and endless possibilities. Happy New Year 2025!
We are glad that our proposed method in The First VoicePrivacy Attacker Challenge has been selected as one of the best-5 systems!
Three of our papers Detecting Spoof Voices in Asian Non-Native Speech: An Indonesian and Thai Case Study, Unsupervised Anomalous Sound Detection Using Timbral and Human Voice Disorder-Related Acoustic Features, and Anomalous Sound Detection Based on Time Domain Gammatone Filterbank and IDNN Model have been presented at the 16th annual conference organized by Asia-Pacific Signal and Information Processing Association (APSIPA 2024).
Our paper Indonesian Speech Content De-Identification in Low Resource Transcripts has been accepted for presentation at The Second Workshop in South East Asian Language Processing (SEALP 2025), Co-loacted with (COLING 2025), Abu Dhabi, UAE. This paper was the collaboration work between ITB (Indonesia) and JAIST (Japan). This work was supported by the JST Sakura Science Exchange Program FY2023.