can you hear me now? AI-Coustics to fight noisy audio with generic AI

Noisy recordings of interviews and speeches are the bane of audio engineers’ existence. But a German startup hopes to fix this with a unique technological approach that uses generative AI to enhance the clarity of voices in videos.

Today, AI-Coustics Emerged in secret with funding of €1.9 million. According to co-founder and CEO Fabian Seipel, AI-Acoustics’ technology goes beyond standard noise suppression to work on any device and speaker.

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

Seipel, an audio engineer by training, co-founded AI-Costics in 2021 with Corwin Jaedicke, lecturer in machine learning at the Technical University of Berlin. Seipel and Jaedicke met while studying audiotechnology at TU Berlin, where they often encountered poor audio. The online courses and tutorials they had to take were quality.

“We are driven by a personal mission to address the widespread challenge of poor audio quality in digital communications,” Seipel said. “Although I had a bit of hearing loss due to music production in my early twenties, I always struggled with online content and lectures, which is why we tackled the topic of speech quality and intelligibility in the first place.”

The market for AI-powered noise-suppressing, voice-enhancing software is already very strong. Competitors to AI-acoustics include InSoundz, which uses generative AI to enhance streamed and pre-recorded speech clips, and Veed.ioA video editing suite with tools to remove background noise from clips.

But Seipel says AI-Coustics has a unique approach to developing AI mechanisms that make real noise…

Read Complete News ➤

Benefits of eating guava for Americans