Revolutionizing Expressive Intelligence with the Open-Source Expression Model – Closing the Valence Gap 

,
Dagmar Damazyn

Continuing our commitment to open innovation, audEERING® has made the expression model freely available on Hugging Face, which has been downloaded 3.7 million times in just two years (since April 6, 2022). This model is the culmination of over two decades of research in affective computing and represents a significant advancement in understanding human expressions through voice analysis. We know what we do and you know how we do: as we are the mother of openSMILE, the first and one of the most known open-source toolkits for audio feature extraction and classification of speech and music signals.

Open-source models vs. the commercial suite

For those looking to enhance the fidelity and application of their projects, audEERING® offers a commercial version of the Expression Module within the devAIce® suite, providing superior analytical precision necessary for high-stakes applications. Look at our limited prepaid offer, which gives you access to all of our devAIce® modules.

The open source model can be tested as part of your research projects and for individual applications. To further increase the quality of the analysis and thus also the project result and the application of a product, the commercial license of the Expression module is required. The module is part of audEERING’s core technology devAIce®. 

Transition to commercial products: The strategic value of devAIce®

After audEERING® creates a solid foundation for testing and research with open-source models, it seamlessly transitions into the area of commercial applications with devAIce®. This suite includes advanced Automatic Speech Recognition (ASR) and Speaker Verification.

devAIce® fuses the developed, trained, and packaged models into several modules and makes Audio AI easy to implement in software and hardware by supporting various platforms and programming languages. With low resource consumption and lightweight code, the highly qualified models run in any project.

Prepaid packages with all AI modules – with a limited offer

Using the devAIce® Web API you can choose between two prepaid options with a limited offer that includes all devAIce® packages.

The Expression module includes various model options. For more information, browse our redesigned website and get in touch with us.

In the 3rd Blog post, we will dive into one of our newest features – Automatic Speech Recognition (ASR).