VoiceDubber Automatically Dubs Your Voice In Other Languages

/in , /by

Mic_000English may have become the default lingua franca of many facets of the Web, but the fact remains that most people online speak a language other than English as their native tongue.

For content producers, the myriad of different languages can be a headache, as it’s costly to reproduce words – spoken or written –

for a multitude of markets. There are free or affordable tools available to circumvent the language barrier – Google has produced subtitling tools, for example, while third-party alternatives are available too.

But what about voiceovers and dubbing? This is where VideoDubber is setting out its stall.

Global Norming

VideoDubber does exactly what its name suggests. The Israeli startup has developed an online SaaS (software as a service) platform that automatically provides voiceovers and dubbing for films, documentaries, TV shows, news broadcasts and any similar broadcasts into more than 30 languages, using synthetic voices. These are based on the voice signature of professional dubbing artists, so it all sounds perfectly natural.

Indeed, VideoDubber claims its technology is able to dub an entire feature film in less than 5 minutes. In the build up to its official launch at IBC next month, VideoDubber has been working with industry partners such as Nuance and the Acapela Group, as well as RRsat, to develop this service. It has also been working closely with Microsoft – it’s a Microsoft BizSpark Plus development partner – and has been licensing some of its speech technology for this initiative, namely Microsoft’s SAPI Text-To-Speech (TTS).

In terms of the target market here, VideoDubber is being aimed at broadcasters and content creators who need to localize masses of content in a short space of time, without breaking the bank.

There is scope for this technology to serve the movie industry in some countries, though perhaps not Hollywood for now.

“This technology is rapidly evolving, and therefore it can serve the movie studios too, depending on the market and the need,” explains Boaz Rossano, CEO of VideoDubber. “In some countries, for example Russia, Latvia, and Poland, the standard of dubbing is voice-over only, and over there automated dubbing could cover almost all needs, including movies.”

There are many facets to what could be construed as ‘dubbing’. Voiceover is actually a separate entity, and usually involves simple narration with minimal, if any, lip-syncing. Also, little attempt is made to place the voiceover artist within the context of the visuals by making their voice suit the surroundings of the on-screen actors (‘echoing’ if in a cave, for example). And all this before we even consider mimicking emotion and intonation, and using different voices for each actor. It’s fair to say that voiceovers are easier to do than full-on dubbing.

Proper dubbing scales all the way up to perfect sync, whereby attempts are made to sync the translated words to the actors’ mouth movements, and position the interpretation so it sounds as though it could be native to the original recording. VideoDubber is planning to integrate voice-intonation technology into its platform in future iterations, while text-to-speech specialists Acapela Group already offer “emotional variants” in its voices.

Moreover, VideoDubber has up to eight different voices per language, with each synthetic voice in its library built using the previous work of a professional narrator as a template.

How it works

VideoDubber doesn’t work with any old video – you will have to possess the subtitle files for it to work, as it uses text-to-speech technology to enable this. So you would upload your .AVI or .MP4 video file, and its corresponding subtitles (in .SRT, .680 or .PAC file formats), to the VideoDubber Web service, fill in a form, and the process kicks off from there. So you could have dubs for your videos in up to 30 languages within a day.

In terms of costs in relation to other localization techniques, Rossano says that VideoDubber will certainly fall below that of professional dubbing production, but will likely be more expensive than subtitling.

“This technology previously used solely in one market has now significantly impacted the broadcast market,” he says. “Text-to-speech can now enable an automated dubbing service that is available 24/7 and can dub masses of video hours to different languages simultaneously, in a small fraction of the time it traditionally took. This is something that will revolutionize the TV market.”

With patents registered, licensing agreements in place with various speech technology providers, and some private equity raised, it’s full steam ahead for VideoDubber as it looks to exit beta next month.

The Next Web

Google+
Facebook Follow
Twitter Follow

First Chinese Winner of Aurora Borealis Award for Translation

/in , /by

xuyuanchongThe 93-year-old Chinese translator Professor Xu Yuanchong has won the “Aurora Borealis” Prize for Outstanding Translation of Fiction Literature earlier this month. It’s one of the highest honors among international translators.

It’s one of the highest honors among international translators. Since it’s set up in 1999 by the International Federation of Translators, this is the first time for a Chinese translator to win such an award. Why was the award given to Xu Yuanchong and what’s his story?

“The reason we give the first prize to Professor Xu Yuanchong has involved his career in building bridges among the world’s Chinese, English and French speaking peoples. He has translated Chinese literature extensively into English and French, as well as having translated major works from western languages into Chinese, and has also published works on translation theory. Jurors took into consideration the vast number of readers around the world who might be reached by Professor Xu Yuanchong’s translations,” said Perpetua Uiterwaal, member of the International Federation of Translators and juror of the panel.

Xu Yuanchong is best-known for his efforts in translating traditional Chinese poems into English and French. His work 300 of China’s Immortal Poems was published by British publishing company Penguin in 1994, and hit the shelves in Britain, U.S., Canada, Australia and other countries.

It’s the first time the publishing company published a Chinese translation. Apart from translating the classical Chinese poetry into foreign languages, Xu also translated many of the British and French classics into Chinese.

In his seventies, he was still involved in translating Proust’s masterpiece, Rememberance of Things Past. He advocates that the versions of poems should combine visual and aural beauties together, and they should reproduce the fusion of pictorial composition and musical arrangement.

But Xu himself didn’t make it to the awarding ceremony for health problems. Jiang Yonggang, Vice Secretary General of Chinese Federation of Translators, read out a speech written by Professor Xu and received the award on his behalf.

“I feel deeply honored to be the first Chinese translator to receive this award. I take this not only as recognition of my personal work in translation, but also more interest in Chinese literature. I have always taken great pleasure in translating Chinese, English and French literature. And I’m still translating at the age of 93. I simply love it,” Jiang said.

Xu was born in 1921 in Nanchang, capital city of east China’s Jiangxi Province. His mother, who was well educated and good at painting, had a great impact on Xu in his pursue of beauty and aesthetic feelings.

His uncle was a translator who translated Chinese plays into English and even had personal connections with the British dramatist George Bernard Shaw. These achievements made Xu develop a profound interest in learning English.

He studied in the best local school, where his English had been outstanding. Then he took foreign language studies at Tsinghua University after he studied abroad. And finally he became a professor in English and French in Peking University.

“Aurora Borealis” Prize for Outstanding Translation of Fiction Literature was set up in 1999, and is given every three years to one translator.

Wang Gangyi, head of the Chinese delegation to the awarding ceremony, speaks highly of Xu’s achievements.

“Professor Xu is an outstanding figure among Chinese translators. He has a though knowledge of both Chinese and western culture, and plays an important role in bringing Chinese culture to the world, and introducing western culture into China,” Wang said.

Xu Yuanchong was awarded the “Lifetime achievements in translation” from the Translators Association of China in 2010.

BEIJING REVIEW.com.cn

Google+
Facebook Follow
Twitter Follow

Doctors, Translators Working Together to Bridge Wikipedia’s Medical Language Gap

/in , /by

Medical_translation.svgDoctors, Translators Working Together to Bridge Wikipedia’s Medical Language GapInternet users from around the world often turn to Wikipedia to answer questions of all kinds. The information offered there includes medical subjects, especially important in parts of the world where access to medical professionals may be limited.

However, much of this information can be unreliable and is available only in the most oft-spoken languages.

A group of experienced Wikipedia editors and medical professionals is trying to change that with the Medicine Translation Project, an effort to improve health care-related topics in English Wikipedia and translate them into other languages, including Hindi, Chinese and Macedonian.

Recently, the Wikimedia Foundation’s Individual Engagement Grant (IEG), a microgrant supporting work on Wikipedia-related activities, granted 10,000 US dollars to the Medicine Translation Project Community Organizing project, which aims to enhance communication and coordination among the team.

The project itself started off in 2011 when Dr. James Heilman and a number of translators from Translators Without Borders, such as Enrique Cavalitto and Ildiko Santana teamed up in an effort to translate medical articles. Since then, the project has exploded into a larger translation forum with hundreds of translators translating articles into almost a hundred different languages.

For Wikimedia projects with a large pool of editors, there has been help from editors to assess what is needed, and what should be translated. On smaller projects the goal is set to get anything on World Health Organization (WHO)’s list of essential medicines, as well as anything about neglected tropical diseases, also from a list by the WHO.

The problem is that there are so many layers of complications in the translation process. After an article has been written and been subject to review to ensure its quality, the article needs to be prepared and proofed for translation, after which translators need to be found. Many of our translators are medical professionals and have in-depth knowledge in their native languages. On the top of it, they dedicate plenty of time on the content creation and translation. This helps to get good quality translations. What this also means is that they seldom have any knowledge of Wiki markup or Wikipedia. Someone else who knows the language in question has to go through links, templates etc. and fix them, proofread the translated content so it is up to scratch and readable.

To fix all this, it is best to have a local Wikipedian who can integrate the text. Most of the work has already been done. But, getting these things right is very crucial, especially on Wikipedias with vast content, where there already is a lot of content to link in.

As for the local language integrators, the idea is to have editors who are willing help out and be an intermediary between that community and our translator community. There is a page where all our finished translations are added. An integrator would patrol that page on a regular basis and inform the respective language Wikipedia that the new translation is ready. The language Wikipedia’s reader community share feedback on the translation quality and suggest for improvement. For us, it is really easy to just add articles without going through them thoroughly. But, that would not work at all. For things to work, the individual must both know Wiki markup and the target language so that the integration can go smoothly.

Global Voices Online

Google+
Facebook Follow
Twitter Follow