NTT showcases technology which can 'correct' Japanese people’s English pronunciation


Depending on the second language you’re trying to master, pronunciation is arguably the hardest aspect to conquer. The Japanese and English languages are no exception. Japanese, with its highly syllabic alphabet, often has a hard time accommodating the often chaotic nature of natural English pronunciation.

While a native English speaker’s tongue might stumble when trying to spit out "makudonarudo" (McDonald's) smoothly the first few times our language allows us to pick it up with a little practice. Japanese English speakers have far more adversity trying to understand all the diminished sounds of a native English speaker casually uttering the name of the famous hamburger chain.

With that, NTT has revealed technology it’s working on that may one day automatically correct a Japanese person’s English pronunciation by editing the speed and rhythm while keeping the original speaker’s voice intact.

This technology, along with several other projects, was put on display at NTT Communication Science Laboratories’ Open House 2013 on June 6-7. Here, the center’s director, Eisaku Maeda, reminded everyone that these products are still very far away from hitting the market but the institute wanted to give people a hands-on experience with future technology.

To give an example of how it works, let’s say a Japanese person spoke the English sentence:

“I will choose the pink one.”

Depending on the person’s abilities it may come out as: “I uiru choosu za pinku one.”

When this voice hits the machine, it will first decode what was being said and then edit the sound data to fit what a native speaker would sound like. Presumably, this is done by editing out the extraneous vowel sounds such as the “u” at the end of pinku. They might also fix up the “l” and “wi” sounds by simply shortening them.

Finally they would just edit out any gaps between words and connect similar sounds like the “s” at the end of “choose” and the “th” at the beginning of “the.” With all the edits made the end result should sound in the words of NTT “native-like.”

The biggest challenge of this project is for the software to accurately make out what the second language speakers are saying. For this, they are also developing highly accurate speech recognition technology.

NTT says that the speech recognition they are currently developing has a 17.9% error rate – considerably lower than the 30.1% rate of currently existing technology. This is accomplished by an algorithm which loops through the audio data and can “learn” the speaker’s particular habits or accents. This also improves the program’s ability to filter out noise from the data with a high degree of accuracy.

It’s unclear to what end this pronunciation smoother would do aside from clear up confusion in foreign restaurants on whether Japanese people want a beer or the bill. NTT is considering if it would be useful for international business presentations and teleconferences.

It could be useful simply as a training device. Hearing your own voice speaking with “perfect” pronunciation could be a good source of motivation to keep up the rigorous vocal training needed for Japanese people interested in eliminating as much accent from their speaking as possible.

Source: IT Media News

Read more stories from RocketNews24. -- Can you understand me now, Google Glass? -- Learning Language Through Nonsense -- 20 Words of English Origin that Japanese People Often Mistake for the Real Thing

© RocketNews24

©2022 GPlusMedia Inc.

Login to comment

Unless the technology is really good, I just imagine people will go around saying really interesting things. I will choose the pink one. Kyle chews the pin, Kwan. I'll chew the pink won. I'll choose the penguin.

3 ( +3 / -0 )

Japanese, with its highly syllabic alphabet, often has a hard time accommodating the often chaotic nature of natural English pronunciation.

This technology will not help much! Japan should get rid of the Katakana syllabary system . It is the reason why Japanese are having a tough time developing their pronunciation in ANY language other than English.

3 ( +4 / -1 )

to master anything you simply need to learn and work it hard.

1 ( +2 / -1 )

Japan should get rid of the Katakana syllabary system

That won't help. The moraic nature of the Japanese language makes epenthesis almost unavoidable for the majority of speakers.

0 ( +0 / -0 )

The problem is how people are taught English. When some of my students say "salada", I asked them to show me the third a in the word. I keep doing this until the student corrects themselves. Even my worst student has learnt to correct themselve. I teach English to children from 1 to 13 year olds. Children under 6 years old don't have a pronunciation problem. They just parrot everything. Katakana words should be banned from Japanese. All it does is encourage laziness.

2 ( +2 / -0 )

Children under 6 years old don't have a pronunciation problem. They just parrot everything.

Except for those whose parents have already 'taught' them English.

0 ( +0 / -0 )

First thing the TV studios should do is to get rid of those "native-English" speakers who speak English with a heavy accent. Sometimes when a "native-English" speaker appears on TV, such as in a drama, I can't understand a word they are saying. Their Japanese is much easier to understand ... so guess that is why the TV studios use them ... thinking if they have mastered Japanese, their English must be perfect.

Either get rid of them ... or insist that they speak understandable English ... if they can ...

0 ( +1 / -1 )

It'll work about as well as Google translation software, making more mistakes than corrections.

0 ( +1 / -1 )

Accents are not that important, studies show that when a person has an accent listeners pay close attention. The only thing Japan needs to do is stop using Katakana English is schools and introduce phonics. Language studies from Canada show that the teacher's pronunciation doesn't affect the learner's pronunciation. Therefore, Japanese teachers should teach phonics and not use Kanatana English in class.

2 ( +2 / -0 )

It better for a child to be bilingual than acquire a second language. There are small drawbacks as a smaller vocabulary but cognitive development would be speeded up and a delay onset of dementia later in life. So if you are a two language house hold, speed the other language at home since the kids will be speaking Japanese outside of the home. Also, it is better for pre-schoolers to hear (a) different langage(s) even if they don't understand it/them. It will make it easier later to pick a language. Your ability to distinguish sounds is better before you are 5 or 6 than after. Since Japanese is a simple language phonetically, having foreign language sounds hard wired would make it easier to pickup new languages later. It also help in diversify of thinking. At least the studies show this. In Japan unlike Europe, there is almost no possibility of hearing and picking other languages. There may not be any advantage in writing ability but maybe some in a Japanese/Chinese household. In an English household, there would be learning advantages for must European languages since most of the alphabet is shared. Maybe Japanese should also teach Hepburn romanji.

0 ( +0 / -0 )

Login to leave a comment

Facebook users

Use your Facebook account to login or register with JapanToday. By doing so, you will also receive an email inviting you to receive our news alerts.

Facebook Connect

Login with your JapanToday account

User registration

Articles, Offers & Useful Resources

A mix of what's trending on our other sites