Asharq News serves as a 24/7 news service that reaches out to the world and beyond with a unique approach: impartial news and in-depth analysis reported through the prism of the economy to empower people in their everyday life. The company recently launched “Asharq Business with Bloomberg” as a multi-platform business news service through an exclusive collaboration with Bloomberg, the world’s leading business and financial information platform. In an effort to boost website traffic and increase user engagement, the Asharq digital services team created an initiative to hyper-personalize website content tailored to individual user preferences and custom-curate global and industry topics for users as new articles and digital content come in from a wide array of multi-language news sources.
To move the initiative forward, the team needed to find a way to manage the enormous volume of multilingual, multi-domain, multi-channel audio, visual, and text content that flowed through the platform and identify/sync key topics to match individual user preferences. Manually tagging and curating the vast repository of media assets proved too costly, time-consuming, and inefficient, so the team instead needed to find a way to automate the discoverability of media assets ingested by the platform.
By tapping into AppTek’s AI-enabled 4D HLT Technologies, including multilingual automatic speech recognition (ASR), neural machine translation (NMT), and natural language processing and understanding (NLU), the team was able to automatically tag and index multi-language media assets as they flowed through the platform which in turn allowed the platform to better detect, extract, understand and analyze the content of interest from various languages and domains with high accuracy while improving the recommendation engine.
AppTek’s 4D technologies further extended the platform by incorporating language identification to better understand the source language of media assets as they arrived to the platform, and integrated NLU/P models to assist with the recognition and extraction of key persons, places, commercial organizations, events, and quotes, as well as analyze sentiment and emotion inside both text and acoustic signals to better understand feelings and attitudes around specific themes, topics, persons, and places.
Nabeel Khatib, General Manager at Asharq News, stated “Implementing AI HLT helped us achieve our search traffic objectives. We are now considering automatic dubbing solutions.”
The Asharq News and Asharq Business with Bloomberg digital services team is currently evaluating AppTek’s automatic dubbing technologies to offer users a more immersive experience for the automatic translation of spoken content in media. This technology fuses automatic speech recognition with timed neural machine translation and adaptive text-to-speech technology including voiceprint, prosody, and volume-emotion for natural-sounding speech to engage users with an experience that simulates the voices of speakers from their source language into a target language. Following is a demonstration of the technology on a current news broadcast:
AppTek.ai is a global leader in artificial intelligence (AI) and machine learning (ML) technologies for automatic speech recognition (ASR), neural machine translation (NMT), natural language processing/understanding (NLP/U), large language models (LLMs) and text-to-speech (TTS) technologies. The AppTek platform delivers industry-leading solutions for organizations across a breadth of global markets such as media and entertainment, call centers, government, enterprise business, and more. Built by scientists and research engineers who are recognized among the best in the world, AppTek’s solutions cover a wide array of languages/ dialects, channels, domains and demographics.
