The evolution of closed captioning from manual stenography to AI-powered automation marks significant progress in making audiovisual content accessible. While today's Automatic Speech Recognition technology delivers impressive accuracy, it struggles with formatting issues, speech disfluencies, and reading speed limitations. AppTek's neural sequence-to-sequence system addresses these challenges by intelligently condensing text—removing low-information content while preserving meaning—without requiring extensive training data or complex parsing rules, ultimately creating more readable captions for all viewers.
Read More
AppTek's Neural Machine Translation (NMT) system was enhanced to better handle specialized content by incorporating three key features during the training phase: glossary integration for consistent terminology translation, markup awareness for proper formatting tag placement, and placeholder handling to maintain code-related variables.
Read More
The SubER (Subtitle Edit Rate) metric is a new standard designed to evaluate the quality of automatically generated subtitles by considering both textual accuracy and timing, addressing unique challenges in subtitle creation. It calculates the edits needed—such as substitutions, deletions, and shifts—to align machine-generated subtitles with a professional reference, offering a more holistic approach than traditional metrics like WER or BLEU. With broad applications in benchmarking and quality assurance, SubER has the potential to become an industry standard for subtitle evaluation, improving the viewing experience by ensuring subtitles are accurate and well-timed.
Read More
Large Language Models (LLMs) is the latest milestone in Natural Language Processing (NLP) and the topic that has captivated the headlines and the attention of the scientific community the world over since the launch of ChatGPT approximately a year and a half ago. Despite the yet unresolved issue of hallucinations which has slowed down the faster and wider adoption of LLMs across all areas of our digital life, the latter have demonstrated impressive capabilities in a wide array of scenarios and tasks, including translation, making our imaginations run wild about the future of multilingual communication.
Read More
We are pleased to announce our new patent(No: US 12,073,177 B2) dated August 27, 2024, for a method and apparatus for improved automatic subtitle segmentation using an artificial neural model.
Read More
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.
