Machine translation is still often dismissed by translators and interpreters as a simplistic word-swapping device, i.e. an automated dictionary that turns sentence A into sentence B by juggling vocabulary. This argument is used every day to suggest that machine translation is inherently limited and, ultimately, pointless. What’s striking is that this misconception mirrors another widespread…
Category: Large Language Models
Reducing Latency in Simultaneous Machine Interpreting with LLMs
I have recently focused my efforts on a major pain point for users of simultaneous speech translation systems: latency. In real-world production environments, it’s not uncommon to see systems with a delay of 8, 10, or even 12 seconds or more, which makes for a frustrating and disjointed experience. The good news is that with…
Private by Design: Rethinking AI Interpreting Beyond the Cloud
In recent weeks, an interpreter made headlines. According to Le Monde, the European Commission dismissed an interpreter suspected of espionage on behalf of Moscow. The individual had reportedly taken notes (while not interpreting) during a high-level, closed-door meeting with Ukrainian President Volodymyr Zelensky in late 2024. The dismissal followed an internal investigation into the interpreter’s…
Trends for 2025 in Technology and Interpreting
Predicting trends is never an exact science—it’s more of an art. Yet, I’m eager to take on the challenge. The good news? At the intersection of Interpreting and Technology I don’t anticipate any dramatic upheavals, apocalyptic scenarios, or seismic disruptions in the space. Change, after all, is a gradual process. Evolution unfolds over time; it…
Rethinking Machine Translation: Understanding, Reformulating, and Translating
What if, instead of taking the direct route from one language to another, we applied the principles taught in translation schools to machine translation? Rather than translating words verbatim, we were trained to understand the meaning of a sentence, then reformulate that meaning — not the sentence itself — in the target language, taking into…
Agency in AI interpreters
Many people hold a static view of what an AI interpreter is or will be: a tool that translates literally and blindly, no matter how unclear or garbled the original speech is—whether it’s mispronounced, unintelligible, or ambiguous. A mechanical device capable only of direct, word-for-word translations. In other words, a piece of software that will…
4 years ago my journey in speech automation started
Four years ago today, my personal journey in the practical implementation of Machine Interpreting started with a simple application -written in a rainy weekend just for fun- which is still available online for free at www.machine-interpreting.com. Try it out if you are curious! Now, commercial speech translation systems are completely different from that first naive…
Visual Cues as Comprehension Aids: the missing Link in Machine Interpreting
Most of the time live communication takes place using both verbal and non-verbal means which are adjusted to the situational needs and communicative objectives of the interlocutors. This obviously plays a crucial role also in multilingual communication and in machine interpretation. For example, typical verbal means can be the so-called topicalization, i.e. positioning the most…
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…