Am I Audible now? AI-coustics to fight noisy audio with generative AI

AI-coustics, a germany based company has recently stealth funding of $2.06 M. The company is hoping to fix the issue of noisy voices during the interviews using generative AI.

“Our core mission is to make every digital interaction, whether on a conference call, consumer device or casual social media video, as clear as a broadcast from a professional studio,” Seipel CEO of Coustics told in his interviews.

Fabian Seipel, an audio engineer co-founded AI-Coustics in 2021, along with Corvin Jaedicke, a lecturer in machine learning at the Technical University of Berlin. They both have come up with the issues of Audio quality they had to face during the tutorials they received or in the online courses. 

Also read: GPT-5 might arrive in mid-2024

We’ve been driven by a personal mission to overcome the pervasive challenge of poor audio quality in digital communications,” Seipel said. “While my hearing is slightly impaired from music production in my early twenties, I’ve always struggled with online content and lectures, which led us to work on the speech quality and intelligibility topic in the first place.”- he added.

To overcome the audio quality issues, they both have introduced a new AI technology that works on the improvement of the quality of each word you speak. The company claims that even with cheap headsets in a room full of noise, you can still sound as if you are recorded in a music room, which actually sounds great.

In this digital world, the market for Audio-suppressing tools is very diverse. There are many AI companies that are a competition for the Coustics team but Seipal claims they as a unique technology that makes them stand out of the crowd. “We developed a unique approach to simulate audio artifacts and problems — e.g. noise, reverberation, compression, band-limited microphones, distortion, clipping, and so on — during the training process,” Seipel said.

Seipel says AI-caustics is focusing on recruiting “diverse” speech sample contributors. He added: “Size and diversity are key to eliminating bias and making the technology work for all languages, speaker identities, ages, accents and genders.”

This technology can be used both in real-time and for recorded audio. Even it can be embedded with smartphones, speakers, and mics to boost the audio quality, especially in a noisy background. AI-Coustics is now offering a real-time audio SDK library available for Windows, Mac, Linux, Web, Android and iOS platforms, that can also be run on Cloud environments.

Also read: AI is going to think like Humans, Nvidia’s Jensen Huang claims

The audio enhancement tool can be a game changer for the Content creation studios.

A content creation studio or broadcast manager can save time and money by automating parts of the audio production process with AI-coustics while maintaining the highest speech quality,” he said. “Speech quality and intelligibility still is an annoying problem in nearly every consumer or pro-device as well as in content production or consumption. Every application where speech is being recorded, processed, or transmitted can potentially benefit from our technology.”