Speech Recognition Breakthrough for the Spoken, Translated Word

Channel:Microsoft Research · Length:9:04 · Published:2012-11-08 · Views:1033789

Watch on YouTube

Summary

Microsoft Research's Rick Rashid demonstrates a speech recognition and translation system, built on deep neural networks, that turns his spoken English into Chinese speech in 2012.

Why HN recommends it

HN cites it as an early impressive real-time speech translation demo, often in discussions of voice-preserving translation and later AI demos.

Check out this real-time translation of spoken English into written and spoken Chinese (in the same voice of the speaker) — HN, 2014

Machine learning & deep learning · Computer vision, speech & NLP

Subtitles (excerpt)

[Music] now I uh I want to come back to the topic of natural user interfaces one of the most natural interfaces for people is human speech and for the last 60 years computer scientists have been trying to find ways to understand and recognize human speech now in the beginning when people first start of tackling this problem they looked at it largely as a pattern matching problem and the earliest systems attempted to take the waveforms that came out of a speaker speaker's voice and matched them up to waveforms that they knew represented certain words unfortunately that approach was extremely fragile partly because everyone speaks differently but also Al even a single speaker will often say the same thing differently depending on the other words or the context in which they're speaking you've probably already noticed me doing that now in the late 1970s there was a major change in the way people decided to do speech recognition this was work being done at Carnegie melon University and the idea was to use a statistical modeling technique in this case hidden Markoff models to make the trans to really be able to take a lot of data from many speakers and produce more robust statistical models of speech now that was a

On Hacker News

They've been doing some really cool stuff for a long time. Check out this real-time translation of spoken English into written and spoken Chinese (in the same voice of the speaker): [VIDEO] — istorical, 2014-03
Have you seen this video from Microsoft, uploaded to YT in 2012, the actual video could be even older: [VIDEO] — Mystery-Machine, 2024-05
Reminds me of this from a few years ago: [VIDEO] I feel like they should merge the two. The subtitles are a nice touch, but if it could capture the voice of the speaker it would be truly magical. — rlu, 2014-05
Wasn't MSRA behind that amazing live English-to-Chinese translator [0]? It's interesting to contrast Google's and Microsoft's approach with ours at Wolfram Research (at 0.3% their size, of course [1]). We've come to see that it is very fruitful to live in a murky space somewhere between "commercial product" and "research project". I'm thinking specifically about Wolfram|Alpha. It's an enormous an… — taliesinb, 2013-08

Related videos