Telos Alliance announced it will demonstrate new AI-driven workflows for its Minnetonka Audio AudioTools Server platform at IBC2025 in Amsterdam.
One of the main features being highlighted is the ability to measure dialog intelligibility, addressing one of the most common complaints across media platforms. The company says the system can extract and process dialogue to improve clarity if measurements indicate potential difficulty for audiences. It adds that isolating dialogue also enables more accurate loudness measurements.
The updated AudioTools Server, version 7, will also introduce an AI-based language detection function. According to Telos Alliance, this feature enables the platform to detect if the dialog is in a language other than expected and then trigger actions such as flagging the content, alerting the operator, or correcting the issue.
Next-level automation
Other machine learning capabilities include speaker identification and diarization, clone detection to verify if a voice is human, content and genre detection and speech-to-text generation.
Costa Nikols, executive strategy advisor for media and entertainment at Telos Alliance, said, “The new features in our AudioTools Server platform, focusing on intelligent operational efficiencies and next-level automation, serve as examples of how the creative use of AI and machine learning enables broadcasters and program distributors to deliver the best possible viewing experience to their television and media audience. Savvy media professionals already count on AudioTools Server to save time and money by automating complex workflows. These new capabilities take that efficiency to the next level and ensure the audience experiences the best audio possible, no matter where and how they view content.”
Telos Alliance is at Booth 8.D37.
These stories might interest you
Telos to debut Zephyr Connect SE at IBC2025