Featured Research

from universities, journals, and other organizations

Norwegian success in creating an artificial child's voice

Date:
February 17, 2012
Source:
The Research Council of Norway
Summary:
“Synthesized speech has grown more and more similar to human speech. Yet children communicating via a speech device are still forced to use a synthetic adult voice,” explains a researcher developing tools to assist disabled persons.

"Synthesised speech has grown more and more similar to human speech. Yet children communicating via a speech device are still forced to use a synthetic adult voice," explains Magne Lunde, Managing Director of Media LT, a company developing tools to assist disabled persons.

This drawback was the driver behind a collaborative research project involving MedialT and Lingit, a software company. Together they are developing Norway's first synthesised childlike voice.

Using funding granted under the Research Council programme ICT for the disabled (IT Funk), they are putting an entirely new method to the test.

Converting the master voice into a comprehensible child's voice

"We start with what is known as a master voice, which is the product of three or four adult speakers recording several thousands of phrases. Then we record a single child reading a smaller number of phrases aloud. We use this recording to modify the master voice, making it sound like a child's voice," relates Torbjørn Nordgård from Lingit. Dr Nordgård is also a professor of linguistics at the University of Nordland.

The phrases recorded by the child have been selected to include a number of the most essential sounds found in Norwegian.

"The master voice still carries the intonation, i.e. a phrase's melody. The result sounds rather like a child with unusual elocution skills, but it's still much better than the voice of an adult," says Mr Nordgård.

Very little research has been carried out on this subject internationally. MediaLT and Linget's innovative method of synthesising a child's voice is bringing them to the forefront of their field.

Everything is now in place to start testing trial versions of the child's voice. "We hope to have a beta version in place this summer," says Magne Lunde.

PC's need to understand children's speech

Mr Lunde and his colleagues are also researching voice control such as use of verbal commands to operate a PC.

In order to operate a computer by means of speech, the machine must successfully decipher what is being said. Interpreting the speech of individuals on both the young and the older end of the scale is especially challenging since the distance from their vocal cords to their lips is shorter than that of the average adult.

"Teaching a speech recognition program to understand the pronunciation of the various sounds of a language requires a relatively large amount of recorded speech. Unfortunately, insufficient data exist today in terms of actual children's speech," states Professor Torbjørn Svendsen from the Norwegian University of Science and Technology.

Professor Svendsen and his research partners have come up with a very elegant, yet simple method of overcoming the challenges associated with speech recognition and children -- they have synthesised children's voices and used the results to compile a collection of data.

A vast improvement in quality

The length of the vocal tract affects the frequency distribution of the speech energy. The researchers are using technology to render the energy distribution of adult speech so that it more closely resembles that of a child.

"The converted adult speech resembles the way children speak in terms of sound as well. Thus, we could apply our conversion technique to a large database of adult speech and generate a functional database of artificial childlike voices. We then used this to train a separate speech recognition program for children," explains Professor Svendsen.

"This greatly improved the recognition fidelity of children's speech. The error rate was reduced by 50 to 70 per cent," he states.

Activities are being carried out in cooperation with the researchers in the Voice control in multimodal dialogue (SMUDI) project, which received funding from the Research Council's Large-scale programme Core Competence and Value Creation in ICT (VERDIKT) and the Ministry of Education and Research.

Norwegian a tough language

The Norwegian language poses a number of especially steep challenges to speech recognition experts.

"In general, the degree of variation in any language is large enough to make it difficult to model. But Norwegian is especially tricky; there are two distinct written forms of the language, countless dialects and a wide range of accepted alternatives for words, declensions and compounds. On top of all this, there is no single pronunciation standard," stresses Torbjørn Svendsen.

Dr Svendsen also points out that people can experience considerable difficulty when faced with voice-controlled devices.

"It is easy to get caught up in our fascination with speech recognition and the many possibilities it holds, so it's important not to replace existing technology when it remains the best option for getting something done -- like using buttons to operate a lift," he concludes.


Story Source:

The above story is based on materials provided by The Research Council of Norway. The original article was written by Norunn K. Torheim/Else Lie; translation by Glenn Wells/Carol B. Eckmann. Note: Materials may be edited for content and length.


Cite This Page:

The Research Council of Norway. "Norwegian success in creating an artificial child's voice." ScienceDaily. ScienceDaily, 17 February 2012. <www.sciencedaily.com/releases/2012/02/120217101337.htm>.
The Research Council of Norway. (2012, February 17). Norwegian success in creating an artificial child's voice. ScienceDaily. Retrieved July 22, 2014 from www.sciencedaily.com/releases/2012/02/120217101337.htm
The Research Council of Norway. "Norwegian success in creating an artificial child's voice." ScienceDaily. www.sciencedaily.com/releases/2012/02/120217101337.htm (accessed July 22, 2014).

Share This




More Mind & Brain News

Tuesday, July 22, 2014

Featured Research

from universities, journals, and other organizations


Featured Videos

from AP, Reuters, AFP, and other news services

Do Obese Women Have 'Food Learning Impairment'?

Do Obese Women Have 'Food Learning Impairment'?

Newsy (July 18, 2014) — Yale researchers tested 135 men and women, and it was only obese women who were deemed to have "impaired associative learning." Video provided by Newsy
Powered by NewsLook.com
Does Mixing Alcohol and Energy Drinks Boost Urge To Drink?

Does Mixing Alcohol and Energy Drinks Boost Urge To Drink?

Newsy (July 18, 2014) — A new study suggests that mixing alcohol with energy drinks makes you want to keep the party going. Video provided by Newsy
Powered by NewsLook.com
Pot Cooking Class Teaches Responsible Eating

Pot Cooking Class Teaches Responsible Eating

AP (July 18, 2014) — Following the nationwide trend of eased restrictions on marijuana use, pot edibles are growing in popularity. One Boston-area cooking class is teaching people how to eat pot responsibly. (July 18) Video provided by AP
Powered by NewsLook.com
Understanding D.C.'s New Pot Laws

Understanding D.C.'s New Pot Laws

Newsy (July 17, 2014) — Washington D.C.'s new laws decriminalizing small amount of marijuana went into effect Thursday. Here's how they work. Video provided by Newsy
Powered by NewsLook.com

Search ScienceDaily

Number of stories in archives: 140,361

Find with keyword(s):
 
Enter a keyword or phrase to search ScienceDaily for related topics and research stories.

Save/Print:
Share:  

Breaking News:
from the past week

In Other News

... from NewsDaily.com

Science News

Health News

Environment News

Technology News



Save/Print:
Share:  

Free Subscriptions


Get the latest science news with ScienceDaily's free email newsletters, updated daily and weekly. Or view hourly updated newsfeeds in your RSS reader:

Get Social & Mobile


Keep up to date with the latest news from ScienceDaily via social networks and mobile apps:

Have Feedback?


Tell us what you think of ScienceDaily -- we welcome both positive and negative comments. Have any problems using the site? Questions?
Mobile iPhone Android Web
Follow Facebook Twitter Google+
Subscribe RSS Feeds Email Newsletters
Latest Headlines Health & Medicine Mind & Brain Space & Time Matter & Energy Computers & Math Plants & Animals Earth & Climate Fossils & Ruins