Tech Papers 2025: Speech-to-speech (STS) conversion is best known for transforming one voice into another. However, its applications extend well beyond straightforward voice replacement. This paper first demystifies STS, explaining how contemporary models analyse prosody, embed timbre, track pitch and resynthesise spectrum to blend a driving performance with a target voice.
On that foundation we present a compact, repeatable workflow that transforms a few minutes of clean speech into a deployable model within a single workday. Five illustrative case studies—reviving archival voices, rescuing noisy location dialogue, executing micro-ADR (additional dialogue recording) text fixes, crafting hybrid character timbres and crosssynthesising musical or animal sounds—demonstrate how the method compresses turnaround times and trims ADR, Sound Effects and scheduling costs, making it ideal for the fast-paced demands of film and television. Although these examples are not STS’s primary commercial drivers, they show how the technology can extend a production’s sonic palette and catalyse innovative, cost-efficient storytelling.
Exclusive Content
This article is available with a Technical Paper Pass
Opportunities for emerging 5G and wifi 6E technology in modern wireless production
This paper examines the changing regulatory framework and the complex technical choices now available to broadcasters for modern wireless IP production.
Leveraging AI to reduce technical expertise in media production and optimise workflows
Tech Papers 2025: This paper presents a series of PoCs that leverage AI to streamline broadcasting gallery operations, facilitate remote collaboration and enhance media production workflows.
Automatic quality control of broadcast audio
Tech Papers 2025: This paper describes work undertaken as part of the AQUA project funded by InnovateUK to address shortfalls in automated audio QC processes with an automated software solution for both production and distribution of audio content on premises or in the cloud.
Demonstration of AI-based fancam production for the Kohaku Uta Gassen using 8K cameras and VVERTIGO post-production pipeline
Tech Papers 2025: This paper details a successful demonstration of an AI-based fancam production pipeline that uses 8K cameras and the VVERTIGO post-production system to automatically generate personalized video content for the Kohaku Uta Gassen.
EBU Neo - a sophisticated multilingual chatbot for a trusted news ecosystem exploration
Tech Papers 2025: The paper introduces NEO, a sophisticated multilingual chatbot designed to support a trusted news ecosystem.
