2025 Conference Program
All Times Pacific Standard Time
Day 1: March 7, 2025
8am: General Introduction
Dr. Ingo Titze
8:15am – 9:15am: Keynote 1: Machine Intelligence Possibilities in Bridging Speech Science and Technology
Dr. Shri Narayanan
| General Topics on AI (Eric Hunter & Ted Mau – Moderators) | ||
| 9:30am – 10am | How Excessive Use of AI May Prevent Scientific Revolutions | Ingo Titze |
| 10am – 10:30am | Interpretable Machine Learning in Voice and Speech Science: Multimodal Analysis Applications | Berardi |
| 10:30am – 11am | Forensic Voice Comparison (FVC) and AI Driven Voice Recognition | Flavia Zuim |
| 11am – 12pm | LUNCH |
| Physics and Physiology (Zhaoyan Zhang & Tobias Riede – Moderators) | ||
| 12pm – 12:30pm | Prediction of Vocal Fold Surface Pressures and Glottal Flow Using Neural Networks | Palaparthi |
| 12:30pm – 1pm | From Imaging to Biophysics, Development of Machine Learning Based Digital Twin System for Voice Research | Zheng |
| 1pm – 1:30pm | Glottal Features Improve Speech Inversion System For Estimating the Velopharyngeal Port Constriction Degree | Tabatabaee |
| 1:30pm – 2pm | Open-Source Manually Annotated Vocal Tract Database for Automatic Segmentation from 3D MRI | Erattakulangara |
Day 2: March 8, 2025
8am: General Introduction
Dr. Ingo Titze
8:15am – 9:15am: Keynote 2: Modeling the Brain Mechanisms Underlying Speech with Biologically Based Neural Networks
Dr. Frank Guenther
| Clinical Applications (Robin Samlan & Karin Cox – Moderators) | ||
| 9:30am – 10am | Detection of Atypical Voices Using a Variational Auto-Encoder Model Based on GRBAS Scales and MFCC Audio Features Derived from Public Voice Datasets | Saldias |
| 10am – 10:30am | Vibrato Metric Machine Learning Models as Diagnostic Biomarkers for Vocal Health, Dysphonia, TMD, and Tremor | Nestorova |
| 10:30am – 11am | Machine Learning vs. Traditional Acoustic Measures in Voice Assessment | Yousef |
| 11am – 12pm | LUNCH |
| Singing Voice and Speech Science (Ron Scherer & Diane Owens – Moderators) | ||
| 12pm – 12:30pm | Pattern Recognition Algorithms for Investigating Neural Activities Underlying Voice Imagery | Salomão |
| 12:30pm – 1pm | Transformation of Relative Acoustic Information Events Into Speech: A System to Be Learned | Story |
| 1:00pm – 1:30pm | A Method Analysis to Explore the Mediating Effects of Commonly Available Artificial Intelligence Voice Extraction Tools on Singing Voice Samples with Piano (A Pilot Study) | Howell |
| 1:30pm | Closing Remarks | Ingo Titze |