A new generation of automated speech-to-text technology that can deliver high quality results for all your audio and video files in batch or real-time mode. The Oliver ASR+ has been trained, apart from the basic speech data, with voice data from contact centers and health related conversations. It includes additional capabilities, like support for PCI, customized keyword spotting or topic detection. The Oliver ASR+ can be deployed on-premises and can output emotion and behavioral metrics, from text, without having to switch applications. Understand your conversations better and arm your sales people with a coaching tool that goes beyond basic transcription.
The Oliver ASR+ module built by our team, through years of engineering experience in speech recognition, linguistics, natural language processing, and deep learning, can be deployed for all sorts of conversations from contact center calls to recorded therapy sessions and virtual assistant interactions. It includes:
+ Trained on Contact Center data
+ On-premises deployment
+ Support for PCI, SSN, number detection and redaction
+ Topic detection and semantic indexing
+ Customized keyword spotting (e.g., detect words like membership, price, subscription)
+ Conversation summary
Enterprise applications can readily integrate our reliable automatic speech recognition solution, the Oliver ASR+, a core component of an #emotionAI deep learning engine based on high-quality human-annotated data. In the future, if your enterprise decides to enrich your application with emotion recognition or behavioral prediction, it can do so directly using the Oliver engine. Oliver can uniquely provide a combination of highly accurate speech-to-text and a rich variety of behavioral measurements and predictions to help you build the application which fully matches your needs. OliverASR+ is just the starting point in this world of endless possibilities..
Whether you’re building a contact center solution, a virtual assistant, or a voice enabled application trust Oliver, the fastest evolving robust emotion AI engine in Voice, to handle your data securely and effectively. Navigate recordings fast and discover the exact part of the speech you’re looking for, bookmark calls according to a topic, and use keywords to explore conversations and improve access to vital information.
Feeling confident in working with APIs and raw outputs? Whether it’s for a virtual assistant on a mobile phone, on the web, in a car, on a smart speaker, or for a social robot, you can now design and build engaging interactions that can seamlessly benefit from our internationally acclaimed speech emotion recognition technology. Introduce Emotion AI for Voice with our robust and fast-evolving OliverAPI
Whether it’s customer experience, quality monitoring or predicting intent we probably have a key performance indicator that can fit your business. If not, we would be more than happy to discuss your pain points and see how our technology can serve your business needs. We will be by your side from development to large scale deployment.
Powered by the