Machine Interpreting and Translation Universals

Today, we’ve made generally available the integration of a Large Language Model (LLM) into KUDO AI Simultaneous Speech Translator. To the best of my knowledge, this marks the first instance of Generative AI being incorporated into a real-life speech translation system. When I began experimenting with LLMs in speech translation, I was immediately struck by … Read more

Situational Awareness in Machine Interpreting

Situational Awareness

Machine Interpreting, a subset of spoken language translation, is undergoing rapid advancements. The recent strides in this domain are particularly evident in the development of robust end-to-end systems. These systems utilize a singular language model to directly translate spoken content from one language to another. As impressive as this technology is, it currently finds its … Read more

New Chapter: Towards AI-enhanced computer-assisted interpreting

I am thrilled to announce my chapter for an upcoming publication on Interpreting and Technology. The chapter titled “Towards AI-enhanced computer-assisted interpreting” delves into the evolution of digital tools for interpreters and the rising influence of artificial intelligence (AI) on Computer-Assisted Interpreting (CAI). As a researcher and practitioner in the field, I have spent the … Read more

Creativity and poetry in the age of AI

The world of artificial intelligence (AI) is rapidly advancing, and recently AI has been used to create impressive works of art, such as realistic pictures or newspaper articles. This has sparked a lot of discussion on the possibility for AI to be truly creative (see this article by Forbes for an overview), with proponent emphasizing … Read more

Interacting with Artificial Intelligence

How do you interact with a Large Language Model? And how do you integrate its knowledge inside a real-life application, for example a bot, a translation system, or something similar? In this short video I show how easy it is to interact with a Large Language Model (LLM), in this case the famous GPT-3, using … Read more

GPT-3 and DALL-E 2 on Interpreting

Interpreting as a Profession Interpreters are important language professionals who facilitate communication between two or more people who do not share a common language. They interpret spoken or written messages from one language into another, ensuring that the meaning is conveyed accurately and faithfully. Interpreters play a vital role in many settings, including courtrooms, conferences, … Read more

I cloned my own voice

Most building blocks of Artificial Intelligence are increasingly plug&play. This means they are accessible to anyone with a basic knowledge of programming (mainly in Python). This is one of the recent revolutions in the field I will never stop emphasizing. If a company makes a product out of it, and you can bet it will … Read more

Improving texts with Artificial Intelligence

A few months ago, I wrote a simple demonstration AI-tool to rephrase and correct text in English. I now added 4 extra languages. The tool supports also French, Italian, Spanish and German. The tool is available for free here: https://www.claudiofantinuoli.org/apps/COR/index.html. If you are curious about how AI can rewrite sentences, what are its potentials and … Read more

Facial emotion recognition may improve automatic speech translation

Meta AI recently published a new framework (AV-HuBERT) to improve automatic speech recognition thanks to lips monitoring, de facto combining Speech with Vision, two of the traditional areas of Artificial Intelligence. Incorporating data on both visual lip movement and spoken language, AV-HuBERT aims at bringing artificial assistants closer to human-level speech perception (see META AI … Read more