AI-driven voice forensics: The threat, power and potential of the human voice

The human voice is the product of a complex biological process that is influenced by myriad factors. Due to the enormous number of parameters that play a role in its production, no two voices in the world are alike. This opens up the possibility of voice being both, an identifier (a biometric) and a descriptor for the speaker. As an identifier, voice is potentially as unique as DNA and fingerprints. As a descriptor, voice is more revealing than DNA or fingerprints. It carries information that can be linked to the current (referring to the time of production) physical, physiological, demographic, medical, environmental and myriad other bio-relevant characteristics of the speaker. This presentation is the story of my journey through the emerging science of human profiling from voice. From hypothesis to algorithm, from inception to state-of-art, it has meandered through voice forensics, acoustics, biology and myriad other fields. It has been studded with triumphs and riddled with challenges, many of which remain unsolved. My work builds on the hypothesis that if any factor whatsoever influences the human mind or body, and if a biological pathway exists between that influence and the voice production mechanism, then there must exist an effect on voice. The challenge lies in discovering and quantifying these effects. Recent breakthroughs include recreating the human face from voice in-vacuo, mechanisms for biomarker discovery, and for the reconstruction of different aspects of the human physical form in 3D from voice.