Skip to content

GTS Blog

by Dave Grunwald, CEO of gts-translation.com

subtitlesDid you ever see a foreign movie that was not dubbed and that had no subtitles? Frustrating, isn’t it. But new software from Google may put an end to that. Youtube just announced that it has moved its automatic speech-recognition and closed-captioning technology out of beta and have now made it available to the YouTube community at large. Read more about it in this PC Magazine article.

Will Google make dubbing movies their next project? With the recent announcements by Google and Microsoft on the advances in speech-to-speech translation, it isn’t hard to imagine the day when movies will be dubbed automatically as soon as they come out. They’ll have to work on some speech synthesis technology to match the pitch and tone of the voices, but I’m sure they will figure that out too.

In this post I am going to describe the process that we use at GTS for post-editing machine translation (MT). To run this process you will need to have licenses for Systran Desktop 6 and SDL Trados Workbench. This process yields human translation quality for various kinds of texts and is well-suited for high volume projects that need to be delivered quickly. We have been successfully using this process for translation of technical translation projects such as tenders and technical manuals.

BACKGROUND

MT has long been considered a tool which is good for ‘gisting’ but that is not good enough for translations that require high quality and accuracy. Several things have happened in the last two years which are changing the way that the translation industry and clients perceive MT: continue reading…

Speech-to-speech translation is gaining momentum. Now Microsoft has jumped into the fray and demonstrated German-English translation of a live conversation between two Microsoft employees. The demo was published by Michael Arrington of Techcrunch.

Google was the first company to announce that it was working on speech-to-speech translation for mobile phones. A previous GTS blog post suggested that IBM and Apple may also be working on this exciting new technology.

Not to be outdone, Microsoft shows its muscle and in my opinion the demo you will see is most impressive. The conversation of the German speaker appears to be unrehearsed and it is translated into English, converted to speech and played back with a very reasonable delay. Seeing this demo, the concept of real-time translation of bilingual conversations appears to be very real and imminent. Implementation on cellular phones may be more challenging and therefore distant, but it is easy to imagine this new Microsoft technology working with Skype and other similar VoIP systems. And it will probably happen sooner than you think.

On Feb. 23, 2010 I published a blog post entitled: Twitter suspends translation project. This post followed an announcement from Twitter that they were not working any more languages at present and had completed localization into FIGS (French, Italian, German and Spanish).

I am pleased to say that my blog post prompted the following response from Matt Sanford (@mzsanford) who is the Tech Lead of Internationalization at Twitter: continue reading…

Microsoft Translator official team blog announced the addition of seven new languages to its online Bing Translator. The new languages are Romanian, Norwegian, Hungarian, Slovak, Slovenian, Lithuanian and Turkish. That brings the total number of languages to 30 which narrows the gap with Google; but Google still has a commanding lead with over 50 languages.