To meet the needs of our users, we are constantly evolving our DeepVA product. The latest version is packed with new features and enhancements that give you greater customizability and improved performance. Read now about our updates that make DeepVA even more powerful and user-friendly.
Text-based dictionaries
We know that users have different needs when analyzing data. That’s why we’ve introduced text-based dictionary management. This new feature allows you to easily customize mining module results to your specific needs. Take control and add your own dictionaries to quickly filter out terms that are relevant to you in Speech Recognition and Lower Third extraction. With DeepVA, customization of your software is now in your hands.
The extracted text paragraphs are now longer for easier handling and further processing. The context of the content can thus be better grasped, and users can edit the text much more easily.
Improved user experience with faster loading of thumbnails
To provide you with a better user experience, we have made optimizations to the loading speed of thumbnails in the user interface. Now you can navigate your media files faster with a more efficient workflow. Spend less time waiting and focus on key insights and analytics.
Real-time service monitoring with the new status page
Ensuring our services are running smoothly is a top priority for us. With the launch of the new status page status.deepva.com, you can now monitor the health of our services in real-time. Stay up to date on any service interruptions, planned maintenance, or performance updates. We believe transparency is key to a seamless user experience, and the status page allows you to get up-to-date information at your fingertips.
We will continue to notify you in advance via email of planned maintenance and any interruptions to system access.
Improved audio analysis with an integrated audio player
By adding an audio player to the job results page, we continue to improve audio-based analysis. You can now play and review audio sources directly on the platform. This integration provides a more comprehensive and streamlined analysis experience, saving you time and effort in accessing and evaluating audio data.
Perfect balance between precision and speed for Speech Recognition function
Users can now choose between two options within the Speech Recognition function – either highly accurate analysis for more precise results or faster processing for audio analysis. The perfect balance between precision and speed opens up exciting possibilities for a wide range of applications and ensures that DeepVA is optimally designed for all needs.
What else is new? Bug Fixes & Co.
- Improved webhook event management: by introducing namespaces, we have revised the names of webhook events to create a clearer and more manageable system. Learn more: https://docs.deepva.com/webhooks/
- Default word-level timestamps: Based on valuable feedback from our users, we have removed word-level timestamps in speech recognition and enabled them by default. This simplifies your workflow and eliminates manual configurations to gain accurate insights from your speech data.
- Bug fixes: We’ve worked hard on bug fixes to ensure a smooth user experience. This includes fixing issues related to audio tracks in source videos. We also fixed an issue where filtering rating feedback in the UI was not working, and another issue where white spaces and umlauts in the file name prevented the source from playing from storage.
- Other optimizations: In addition to the above improvements, we also fixed minor bugs and further optimized the overall functionality and reliability of the DeepVA software.
Try the latest version of DeepVA and experience the power of AI-driven analytics with advanced customization and improved performance. Discover the limitless possibilities and get deeper insights with DeepVA’s cutting-edge features.
All DeepVA changelog updates are available here: https://docs.deepva.com/changelog/
