Sayaka Shiota
Sayaka Shiota, Associate Professor
Speech Information Processing / Speaker Recognition / Spoofing Speech Detection / Voice Privacy / Deep learning
Our laboratory conducts research on speech and audio processing technologies based on deep learning. Our research focuses on three main areas: speaker recognition and verification using voice biometrics, spoofing detection to counter synthetic and deepfake voice attacks, and speech privacy protection techniques to safeguard personal information. We aim to develop robust authentication systems that maintain high accuracy while simultaneously preserving user privacy. By integrating these research domains, we strive to create secure and privacy-preserving voice-based systems that can be reliably deployed in real-world applications.
