Steve Clayton: Speak New Languages Instantly With Microsoft Tech

Steve Clayton: Speak New Languages Instantly With Microsoft Tech

This voice recognition software translates your speech and then uses your own voice to talk in another language.

Steve Clayton, Microsoft
  • 12 november 2012

Contributed by Rick Rashid, Microsoft’s Chief Research Officer

A demonstration I gave in Tianjin, China at Microsoft Research Asia’s 21st Century Computing event has started to generate a bit of attention, and so I wanted to share a little background on the history of speech-to-speech technology and the advances we’re seeing today.

In the realm of natural user interfaces, the single most important one – yet also one of the most difficult for computers – is that of human speech.

For the last 60 years, computer scientists have been working to build systems that can understand what a person says when they talk.

In the beginning, the approach used could best be described as simple pattern matching. The computer would examine the waveforms produced by human speech and try to match them to waveforms that were known to be associated with particular words.

While this approach sometimes worked, it was extremely fragile. Everyone’s voice is different and even the same person can say the same word in different ways. As a result these early systems were not really usable for practical applications.

In the late 1970s a group of researchers at Carnegie Mellon University made a significant breakthrough in speech recognition using a technique called hidden Markov modeling which allowed them to use training data from many speakers to build statistical speech models that were much more robust. As a result, over the last 30 years speech systems have gotten better and better. In the last 10 years the combination of better methods, faster computers and the ability to process dramatically more data has led to many practical uses.

Today if you call a bank in the US you almost certainly are talking to a computer that can answer simple questions about your account and connect you to a real person if necessary. Several products on the market today, including XBOX Kinect, use speech input to provide simple answers or navigate a user interface. In fact our Microsoft Windows and Office products have included speech recognition in them since the late 90’s. This functionality has been invaluable to our customers with accessibility needs.

Until recently though, even the best speech systems still had word error rates of 20-25% on arbitrary speech.

Just over two years ago, researchers at Microsoft Research and the University of Toronto made another breakthrough. By using a technique called Deep Neural Networks, which is patterned after human brain behavior, researchers were able to train more discriminative and better speech recognizers than previous methods.

During my October 25 presentation in China, I had the opportunity to showcase the latest results of this work. We have been able to reduce the word error rate for speech by over 30% compared to previous methods. This means that rather than having one word in 4 or 5 incorrect, now the error rate is one word in 7 or 8. While still far from perfect, this is the most dramatic change in accuracy since the introduction of hidden Markov modeling in 1979, and as we add more data to the training we believe that we will get even better results.

Machine translation of text is similarly difficult. Just like speech, the research community has been working on translation for the last 60 years, and as with speech, the introduction of statistical techniques and Big Data have also revolutionized machine translation over the last few years. Today millions of people each day use products like Bing Translator to translate web pages from one language to another.

In my presentation, I showed how we take the text that represents my speech and run it through translation- in this case, turning my English into Chinese in two steps. The first takes my words and finds the Chinese equivalents, and while non-trivial, this is the easy part. The second reorders the words to be appropriate for Chinese, an important step for correct translation between languages.

Of course, there are still likely to be errors in both the English text and the translation into Chinese, and the results can sometimes be humorous. Still, the technology has developed to be quite useful.

Most significantly, we have attained an important goal by enabling an English speaker like me to present in Chinese in his or her own voice, which is what I demonstrated in China. It required a text to speech system that Microsoft researchers built using a few hours speech of a native Chinese speaker and properties of my own voice taken from about one hour of pre-recorded (English) data, in this case recordings of previous speeches I’d made.

Though it was a limited test, the effect was dramatic, and the audience came alive in response. When I spoke in English, the system automatically combined all the underlying technologies to deliver a robust speech to speech experience—my voice speaking Chinese. You can see the demo in the video above.

The results are still not perfect, and there is still much work to be done, but the technology is very promising, and we hope that in a few years we will have systems that can completely break down language barriers.

In other words, we may not have to wait until the 22nd century for a usable equivalent of Star Trek’s universal translator, and we can also hope that as barriers to understanding language are removed, barriers to understanding each other might also be removed. The cheers from the crowd of 2000 mostly Chinese students, and the commentary that’s grown on China’s social media forums ever since, suggests a growing community of budding computer scientists who feel the same way.

Originally posted on Next at Microsoft. Republished with kind permission.


Dubai And The Future Of Humanitarian Design

Design & Architecture
Technology october 21, 2016

Concept Camera Designed To Only Take Unique Photos

Camera Restricta is tool that prompts photographers to only capture one-of-a-kind images

Design & Architecture october 21, 2016

Fragrance Will Release The Smell Of Data If Your Private Information Is Being Leaked

The device is designed to create a physical cue for the potential dangers lurking online


Get PSFK's Related Report: Future of Automotive

See All
Retail october 21, 2016

LYNK & CO Is A New Auto Brand That Promises Mobile Connectivity On Wheels

Online access and mobility sharing are driving the company to disrupt the auto industry

Related Expert

Soraya Darabi

Retail, Technology & Collaboration

Travel october 21, 2016

Become A Citizen Of The First Nation In Space

Asgardia is a new concept for a floating society above Earth

Entertainment october 21, 2016

Speaker Displays Song Lyrics As Music Is Played

The device is able to generate the graphics on a translucent screen and retrieve the words from a connected database

AI october 21, 2016

Travel Assistant Scans Your Emails To Make Planning Easier

This AI add-on will sync with your inbox and sends reminders to make sure you don't miss anything important


Future Of Automotive
Scenarios Driving The Digital Transformation Of An Industry

PSFK Op-Ed october 21, 2016

Health Expert: Nutritional Meal Replacements Are A Solution To Corporate Wellness

Ample Foods Founder Connor Young explains why supplements are the next food trend coming to the workplace

PSFK Labs october 21, 2016

PSFK Picks: Top 5 Performance-Enhancing Wearables

Our new report looks at innovations pioneering the future of performance through intelligent activewear and predictive analytics

Millennials october 21, 2016

FOMO Survival Kit Helps Millennials Cope With Social Anxieties

The satirical product is meant to be a playful diversion for people who feel like they are missing out

Food october 21, 2016

New York Restaurant Uses Tomato Sushi As Its Newest Meat Alternative

fresh&co is using sous vide Roma tomatoes to create a vegan option that has the texture and taste of tuna

Advertising october 21, 2016

Red Bull Converts Sao Paulo Payphones Into Data-Driven Bus Schedules

The booths allow city residents to check local transit times through a simple toll-free phone call

Retail october 21, 2016

Why Experiential Events Could Replace Trade Shows

Marketers are seeking creative and impactful new ways to connect with influencers

Children october 21, 2016

Modular Kit Teaches Kids How To Make Their Own Robots

MODI features magnetic modules and a platform for programming to encourage experimentation

Infants october 21, 2016

Work Table Doubles As A Baby Seat

Designer Kunsik Choi created the furniture to facilitate emotional communication between between parents and their children

Technology october 21, 2016

Album Turns Into Something New Each Time It’s Streamed

Bill Baird's new album explores the relationship between time and music through a website crafted by design team, One Pixel Wide

Technology october 21, 2016

Wearable Device And Lamp Recreate Beautiful Sunsets In Your Home

Sun Memories can record up to six hours of natural light and reproduce it via a connected light at a later date

No search results found.