News
Current updates
We're excited to announce the publication of our latest research in the Journal of the Audio Engineering Society. This research explores the intersection of forensic science and speech technology aiming to ensure reliable understanding of poor-quality speech recordings used as evidence in criminal trials.
We successfully organized the 3rd ASEAN-IVO meeting and JAIST-ASEAN deepfake detection hub symposium. We welcomed participants from NICT, Japan and ASEAN institutions from Thailand, Indonesia, Brunei Darussalam, and Myanmar. The meetings were a resounding success, generating excitement and enthusiasm among all participants. The collaborative discussions and knowledge sharing fostered a vibrant atmosphere, laying the groundwork for future collaborations in spoof detection research.
Our paper Indonesian Speech Anti-Spoofing System: Data Creation and Convolutional Neural Network Models has been presented by our student, Ms. Sarah Azka Arief, at the 11th International Conference on Advanced Informatics: Concepts, Theory, and Applications (ICAICTA 2024), Singapore.
Our paper MAG-BERT-ARL for Fair Automated Video Interview Assessment has been accepted for publication in IEEE Access. This paper was the collaboration work between UI (Indonesia) and JAIST (Japan). This work was supported by the JST Sakura Science Exchange Program FY2023.
Our papers 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 accepted for presentation at the 16th annual conference organized by Asia-Pacific Signal and Information Processing Association (APSIPA 2024). These papers were the collaboration work between ITB (Indonesia) and JAIST (Japan). This work was supported by the JST Sakura Science Exchange Program FY2023.
Our paper Detecting Spoof Voices in Asian Non-Native Speech: An Indonesian and Thai Case Study has been accepted for presentation at the 16th annual conference organized by Asia-Pacific Signal and Information Processing Association (APSIPA 2024).
Our papers UCSYSpoof: A Myanmar Language Dataset for Voice Spoofing Detection and Analysis of Pathological Features for Spoof Detection have been accepted for presentation at the 27th International Conference of the Oriental COCOSDA. These papers were the collaboration work between UCSY (Myanmar), NECTEC (Thailand), and JAIST (Japan). They were also a part of the ASEAN IVO project titled ‘Spoof Detection for Automatic Speaker Verification’(www.nict.go.jp/en/asean_ivo).
I participated in the 4th Symposium on Security and Privacy in Speech Communication and 3rd VoicePrivacy Challenge, Kos Island, Greece. This event is a satellite event of Interspeech. I served as a member of program committee and one of session chairs during the VPC presentations.
I participated in the Interspeech 2024, Kos Island, Greece. Our paper Are Recent Deep Learning-Based Speech Enhancement Methods Ready to Confront Real-World Noisy Environments? was presented as a poster presentation and received a lot of visitors from academia, industry, and others. I am very glad to be able to participate in this conference on-site for the first time!
Our paper Indonesian Speech Anti-Spoofing System: Data Creation and CNN Models has been accepted for presentation at the 11th International Conference on Advanced Informatics: Concepts, Theory, and Applications (ICAICTA 2024). This paper was the collaboration work between ITB (Indonesia) and JAIST (Japan).
One of my co-advise undergraduate student (Sarah Azka) from Institut Teknologi Bandung finished her final defense. お疲れ様でした!
Our paper about Forensic speech enhancement has been accepted for publication in the Journal of the Audio Engineering Society. This initiation introduces an innovative interdisciplinary project aiming to ensure reliable understanding of poor-quality speech recordings used as evidence in criminal trials.
Our paper Do We Need to Watch It All? Efficient Job Interview Video Processing with Differentiable Masking has been accepted for presentation at the 26th ACM International Conference on Multimodal Interaction (ICMI 2024).
Our application for the JAIST Grant for the establishment of an advanced research base (JAIST Science Hub)) 2024 (令和6年度先端研究拠点形成支援（JAISTサイエンスハブ構築支援）) was accepted.
Our application for the JAIST Grant for fundamental research FY2024 (令和6年度研究拠点形成支援事業（萌芽的研究）) was accepted.
Three of my co-advise undergraduate students (Primanda, Malik, and Rifqi) from Institut Teknologi Bandung finished their final defense. お疲れ様でした!
I joined the fifth Virtual Conference on Computational Audiology, VCCA2024 online.
One of my co-advise undergraduate student (Bimasena) from Universitas Indonesia finished his final defense. お疲れ様でした!
Our paper Incremental Multimodal Sentiment Analysis on HAI Based on Multitask Active Learning with Inter-Annotator Agreement has been accepted for presentation at the 12th International Conference on Affective Computing and Intelligent Interaction (ACII 2024).
Our paper Are Recent Deep Learning-Based Speech Enhancement Methods Ready to Confront Real-World Noisy Environments? has been accepted for presentation at the 25th Interspeech Conference.
Our paper was presented in the 5th International conference on Industrial Engineering and Artificial Intelligence (IEAI 2024), Chulalongkorn University, Bangkok, Thailand. Our paper received the Best Presentation award at the conference.
New year, new goals! Let's make FY 2024 a productive and fulfilling year in research and beyond!
We had a graduation ceremony for nine master students from Okada laboratory and one of my co-advise student from Unoki laboratory. Congratulations and best wishes for your next journey!
I participated in the 2024 Spring meeting of the Acoustical Society of Japan (ASJ), Takushoku University(Bunkyo Campus), Tokyo, Japan.
Our paper was presented in 2024 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing, Alamoana Hotel, Honolulu, Hawaii.
Our paper Exploring a Cutting-Edge Convolutional Neural Network for Speech Emotion Recognition has been accepted for presentation at the 5th International conference on Industrial Engineering and Artificial Intelligence (IEAI 2024).
We have a laboratory party to celebrate master students who have successfully passed their defense and also for many other good news! :D
Nine master students from Okada laboratory finished their final defense. One of my co-advise student from Unoki laboratory also finished her final defense and Ph.D entrance examination. お疲れ様でした!
We have JAIST-UI-ITB Human Information Science Hub Symposium and farewell party.
We are glad to welcome ten students from UI and ITB (Indonesia) to JAIST (19 January - 8 February 2024). They participate in the JST Sakura Science Program. Five students have been assigned to the Sakti laboratory. I am co-advising three students who have been assigned to the Unoki laboratory, and two students who have been assigned to the Okada laboratory. We also have a welcome party with Indonesian community in JAIST.
Wishing you a Happy New Year 2024 filled with hope and joy! Our heartfelt condolences go out to those affected by the recent 7.6M earthquake in Noto region of Ishikawa prefecture. While we felt its impact and encountered some equipment damage, our campus remains intact, and we are resuming our regular activities.
Our paper Study on Inaudible Speech Watermarking Method Based on Spread-Spectrum Using Linear Prediction Residue has been accepted for presentation at The 2024 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing.
We had a second collaboration meeting on ASEAN-IVO project titled 'Spoof detection for automatic speaker verification' at Bandung, Indonesia.
Our papers were presented in The 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP 2023), Bangkok, Thailand.
I participated in the Joint Workshop of VoicePersonae and ASVspoof 2023, Tokyo, Japan.
I am truly honored to have been given the opportunity to deliver a lecture on Voice Biometrics and Secure Speech Communication in the IF4071 Speech Processing course at the School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Indonesia.
I had the privilege of presenting on 'Advancements in Speech Signal Processing for Security and Voice Privacy Protection' at the Speech and Hearing Research Group (SpandH) and CDT seminar held in the Ada Lovelace Room, Regent Court, University of Sheffield. Despite the briefness of my research visit, I gained valuable insights and knowledge, thanks to the guidance of Prof. Jon Barker and the welcoming atmosphere provided by my colleagues at the SpandH laboratory.
Grateful to have had the opportunity to visit Prof. Trevor Cox at the University of Salford, Manchester, UK. He generously guided us through a laboratory tour, providing explanations of the various experiment rooms within the Acoustic and Audio Engineering department.
Our paper ThaiSpoof: A Database for Spoof Detection in Thai Language has been accepted for presentation at The 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing and The International Conference on Artificial Intelligence and Internet of Things (iSAI-NLP 2023).
Our paper Spoof Detection using Voice Contribution on LFCC features and ResNet-34 has been accepted for presentation at The 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing and The International Conference on Artificial Intelligence and Internet of Things (iSAI-NLP 2023).
Mr. Tran Duc Minh, Mr. Hung Le, Mr. Daiki Tokieda (Tokyo Satelite) from Okada laboratory and Mr. Haowei Cheng from Unoki laboratory got their master degree. Many congratulations!
Our paper Non-Intrusive Speech Intelligibility Prediction Using an Auditory Periphery Model with Hearing Loss has been accepted for publication in Applied Acoustics.
I am undertaking a six-week research visit (September 11 - October 20, 2023) in the Speech and Hearing Research Group (SpandH), Department of Computer Science, at the University of Sheffield, UK under the supervision of Prof. Jon Barker.
We presented our work in the 31st European Signal Processing Conference (EUSIPCO 2023), Helsinki, Finland.
Our paper Analysis of Spectro-Temporal Modulation Representation for Deep-Fake Speech Detection has been accepted for presentation at The 15th Asia-Pasific Signal and Information Processing Association (APSIPA ASC 2023).
Our paper Incorporating the Digit Triplet Test in A Lightweight Speech Intelligibility Prediction for Hearing Aids has been accepted for presentation at The 15th Asia-Pasific Signal and Information Processing Association (APSIPA ASC 2023).
Mr. Tran Duc Minh and Mr. Hung Le from our laboratory have finished their master defense. Congratulations!
We presented our work in the 4th Clarity Workshop on Machine Learning Challenges for Hearing Aids (Clarity-2023), co-located with Interspeech 2023.
The 3rd Symposium on Security and Privacy in Speech Communication (SPSC), co-located with Interspeech 2023, was successfully held in a hybrid format.
We (a team from Okada lab) participated the local event 'Eastern Regional Ekiden Race (第50回 東部地区駅伝大会)'.
Mr. Haowei Cheng and Ms. Fanda Yuliana Putri from Unoki laboratory have finished their master defense. Congratulations!
I am honored to be given an opportunity to give an invited talk at APSIPA Workshop on Signal and Information Processing in Indonesia 2023, Institut Teknologi Bandung, Indonesia.
We presented our work at The 25th HCI International Conference, HCII 2023, Copenhagen, Denmark.
I participated in The 25th HCI International Conference, HCII 2023, Copenhagen, Denmark.
Our application for the JAIST Grant for fundamental research FY2023 (令和５年度研究拠点形成支援事業（萌芽的研究）) was accepted.
Our application for the Kakenhi Grant-in-Aid for Challenging Research (Exploratory) FY2023 (R5挑戦的研究（萌芽)) was accepted.
Our paper A Ranking Model for Evaluation of Conversation Partners Based on Rapport Levels has been accepted for publication in IEEE Access.
We had a kick-off meeting of the ICT Virtual Organization of ASEAN Institutes and NICT (ASEAN-IVO) with project titled "Spoof Detection for Automatic Speaker Verification". This meeting was held as a hybrid meeting at Bangkok, Thailand.
Our paper Auditory Model Optimization with Wavegram-CNN and Acoustic Parameter Models for Nonintrusive Speech Intelligibility Prediction in Hearing Aids has been accepted for presentation at The 31st European Signal Processing Conference (EUSIPCO 2023).
I am honored to be given an opportunity to share knowledge about AI for speech processing in AI Talks ITB #10: "Threats and Opportunities of Voice-Interactive Applications".
The new fiscal year (FY2023) has been started! May we always full of hope in our hearts so that we can enjoy and utilize our precious time this year to the fullest!
We celebrated the graduation of five master students (Tomoya Ohba, Ryusei Kimura, Ryota Matsukuma, Ko Murase, and Kazuki Kuba) and two Ph.D. students (Li XiSia and Hidetoshi Kawaguchi) from Okada laboratory. Tomoya Ohba also obtained the student outstanding performance award. Many congratulations!
We had a collaborative meeting between JAIST-RIEC in Tohoku University, Sendai, Japan.
Five master students from our laboratory finished their final defense. お疲れ様でした!
Dr. Hidetoshi Kawaguchi from our laboratory has finished his Ph.D defense with topic "Research on collaborative machine learning with a human expert for supporting network operations". Congratulations!
Dr. Sixia Li from our laboratory has finished his Ph.D defense with topic "Zero-shot slot filling based on multi-aspect intrinsic representations from multiple aspects". Congratulations!
Our paper Inter-person Intra-modality Attention Based Model for Dyadic Interaction Engagement Prediction has been accepted for presentation at HCI International 2023.
Our paper Investigating the Effect of Linguistic Features on Personality and Job Performance Predictions has been accepted for presentation at HCI International 2023.
Our paper Personality Trait Estimation in Group Discussions using Multimodal Analysis and Speaker Embedding has been accepted for publication in Journal on Multimodal User Interfaces.
We are glad to welcome four faculty members and ten students from UI and ITB (Indonesia) to JAIST (5-25 January 2023). They participate in the JST Sakura Science Program. I am especially thankful for being able to meet my former advisors (Dr. Dessi Puji Lestari and Dr. Ayu Purwarianti) on our campus.
One student from Okada laboratory (Shun Katada) has completed his Ph.D course and obtained the Outstanding Performance Award from School of Information Science. Many congratulations!
We presented our work at the The 18th Australasian International Conference on Speech Science and Technology (SST 2022), Canberra, Australia.
We presented our work at the The 21st International Conference on Mobile and Ubiquitous Multimedia (MUM 2022), Lisbon, Portugal.
We had a collaborative meeting between JAIST-SIIT-NECTEC in Bangkok, Thailand.
We presented our work at the Asia Pacific Signal and Information Processing Association Annual Summit and Conference 2022 (APSIPA ASC 2022), Chiang Mai, Thailand.
Our paper Multimodal Analysis for Communication Skill and Self-Efficacy Level Estimation in Job Interview Scenario has been accepted for presentation at the The 21st International Conference on Mobile and Ubiquitous Multimedia (MUM 2022).
We presented our work at the 2nd Symposium on Security and Privacy in Speech Communication joined with 2nd VoicePrivacy Challenge Workshop.
Two master students from Okada laboratory (Gao Yuan and Keita Ando) have completed their master course. Many congratulations!
Our paper F0 Modification via PV-TSM Algorithm for Speaker Anonymization Across Gender has been accepted for presentation at the Asia Pacific Signal and Information Processing Association Annual Summit and Conference 2022 (APSIPA ASC 2022).
Our paper Speech Intelligibility Prediction for Hearing Aids Using an Auditory Model and Acoustic Parameters has been accepted for presentation at the Asia Pacific Signal and Information Processing Association Annual Summit and Conference 2022 (APSIPA ASC 2022).
Our paper OBISHI: Objective Binaural Intelligibility Score for the Hearing Impaired has been accepted for presentation at the The 18th Australasian International Conference on Speech Science and Technology.
I receive the Kakenhi Research Activity Start-up 2022 (R4科研費(研究活動スタート支援)) FY2022.
An article about my life in JAIST has been posted at JAIST International Student News (2022).
I receive the Research grant for fundamental research (萌芽的研究支援), JAIST FY2022.
Our paper Speaker Anonymization by Pitch Shifting Based on Time-Scale Modification has been accepted for presentation at the Security and Privacy in Speech Communication (SPSC) Symposium 2022.
We presented our work at the 2nd Clarity Workshop on Machine Learning Challenges for Hearing Aids.
New website was published.
I have started an assistant professor position at Social Signal Interaction Group, JAIST.