McLean, VA, January 23, 2019 – AppTek, a leader in Artificial Intelligence, Machine Learning, Automatic Speech Recognition and Machine Translation, today announced it has been awarded a patent by the United States Patent Office for its innovation in Automatic Speech Recognition (ASR) technology which enables higher precision and recall of keywords in spoken content by using a textual keyword list. This transforms the process of listening to audio and mining that content without the need for a full transcript. In this patent, AppTek uses its unique fuzzy phonetic search, vigorous search validation, and localized ASRs with customized lexicon to improve precision and recall and to include the keyword’s context for end users.This is a much faster, easier, and more accurate way of keyword spotting in real-time or across repositories.
This development democratizes access to audio content for anyone who can upload a list of keywords to search against spoken content in various languages. AppTek AI-based system will take a user’s list and map text to phonetic representations of the words, use a Deep/Recurrent Neural Networksto learn spoken words, and tune for dialect and acoustic characteristics. The result is faster, easier and more precise search and retrieval.
AppTek’s innovation uses the content adjacent to the keyword phonemes to anticipate keyword usage, qualify the match and provide faster and more contextually relevant matches. It also addresses spoken dialects by allowing users to define customized pronunciations. Ultimately, these advances provide a more accurate capability for audio analysis based on context or use case.
For example, customer interaction or marketing managers can review text from captured audio segments that may contain keywords of interest, such as “cancel” or other expressions of customer frustration. Frequency of keywords can be assessed in a single audio file or across multiple audio files, as well as the context in which a word appears. This can identify issues that management can address through changes to things like call scripts.
AppTek CEO Mudar Yaghi said “This development improves upon other ways of real-time capture and analysis of audio content from any source and across multiple languages and dialects.”
AppTek artificial intelligence and machine learning-based automatic speech recognition and machine translation platform is deployed for the media and entertainment industry as well as call centers. Leveraging over 30 years’ worth of experience its scientists and research engineers support the research and development of practical systems – AppTek enables the highest quality automatic speech recognition and machine translation solutions available anywhere for enterprises everywhere. The streaming real-time combination allows for live closed captioning and speech to speech translation as in the Apptek closed captioning appliance available to TV stations and the Talk2me® app available on the AppStore. Apptek’s ASR and Neural MT are also available via its cloud API services.
For more information, please visit http://www.apptek.com/technology/.
AppTek provides an artificial intelligence and machine learning-based automatic speech recognition, machine translation and natural language understanding platform for organizations in a variety of markets, such as media and entertainment, call centers, government, enterprise business and others across the globe. Available via the cloud or on-premise, AppTek delivers the highest quality real-time streaming and batch speech technology solutions in the industry. Featuring scientists and research engineers who are recognized amongst the best and most experienced in the world, the company’s solutions cover a wide array of languages, dialects, and channels.