Voice Source Tracking Technology Based on Perceptual Hash of Fingerprint Image
Lin Liu, Wenbo Guo, Peng Jia · 2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC) · 2021
From the perspective of Perceptual Hashing technology, the paper studies the application of Perceptual Hashing of speaker's biological fingerprint image in voice information source tracking proposes three schemes of Perceptual Hashing generation of fingerprint image based on barycenter, pixel expectation and barycenter angle. It embeds the generated Perceptual Hashing value of fingerprint image into speech information as a watermark. When the source of voice information needs to be tracked, the perceptual hash value extracted from the voice information is compared with the perceptual hash value of fingerprint image database to realize the tracking of voice source. Simultaneously, the robustness, anti-collision and security are analyzed. The experimental results show that the scheme has strong robustness and meets perceptual hash uniqueness and security requirements.