AI-based text analytics for audio data

AppTek and  have entered into a strategic technology partnership to bring AI-based text analytics to dynamic audio content in multiple languages. The partnership leverages AppTek's leadership in Automatic Speech Recognition (ASR) and Neural Machine Translation (NMT) technologies with's natural language understanding (NLU) capabilities to enable organizations to leverage audio content in the unstructured data sets that they manage for improving decision making and augmenting intelligent automation.

As organizations increasingly utilize language data - emails, documents, reports and other free form text - for an ever-growing range of enterprise use cases (knowledge discovery, contract analysis, policy review, email management, text summarization, classification, entity extraction, etc.), natural language capabilities will play a critical role in powering any process or application that relies on unstructured language data.

The combined capabilities of AppTek and enhance enterprise and government NLU and NLP (natural language processing) applications, expanding the data types and sources available for analysis to provide even more informational output.

"This partnership brings the full stack Human Language Technology to the federal and commercial space in both Europe and the United States. As we cover multiple sources and types of information input together, we address the full scope of recognition, cognition, interpreting and analytics," said Michael Veronis, Chief Revenue Officer at AppTek. "We look forward to implementing our joint vision."

Using AppTek's speech-to-text technology within the Platform, organizations can automatically transcribe audio types from different sources, including high-quality media broadcast content, podcasts, meetings, one-to-one interviews or even low-bandwidth telephone conversations. In addition, they can leverage advanced multilingual functionalities to generate highly accurate, customizable and scalable translations across hundreds of language pairs.

"The challenges posed by different languages and dialects along with the constraints of speech-to-text accuracy are causing organizations to miss out on the massively unexploited value of language data, especially audio content," said Colin Matthews, Chief Revenue Officer at 

"We are thrilled for this partnership, since AppTek technologies for automating speech recognition and machine translation complement our AI-powered natural language capabilities by harnessing the potential of dynamic multilanguage audio content within the Platform.",