Preset-Voice Matching for Privacy Regulated Speech-to-Speech Translation Systems
This addresses privacy and regulatory concerns for industry users of S2ST systems, though it is an incremental approach focusing on voice matching rather than a fundamental breakthrough.
The paper tackles the problem of privacy and misuse risks in speech-to-speech translation (S2ST) systems by proposing a regulated framework called Preset-Voice Matching (PVM), which matches input voices to consenting preset voices to avoid cloning, resulting in improved run-time and speech naturalness.
In recent years, there has been increased demand for speech-to-speech translation (S2ST) systems in industry settings. Although successfully commercialized, cloning-based S2ST systems expose their distributors to liabilities when misused by individuals and can infringe on personality rights when exploited by media organizations. This work proposes a regulated S2ST framework called Preset-Voice Matching (PVM). PVM removes cross-lingual voice cloning in S2ST by first matching the input voice to a similar prior consenting speaker voice in the target-language. With this separation, PVM avoids cloning the input speaker, ensuring PVM systems comply with regulations and reduce risk of misuse. Our results demonstrate PVM can significantly improve S2ST system run-time in multi-speaker settings and the naturalness of S2ST synthesized speech. To our knowledge, PVM is the first explicitly regulated S2ST framework leveraging similarly-matched preset-voices for dynamic S2ST tasks.