Featured Research

from universities, journals, and other organizations

How Computers Learn To Listen: Scientists Develop Model To Improve Computer Language Recognition

Date:
August 16, 2009
Source:
Max-Planck-Gesellschaft
Summary:
We see, hear and feel, and make sense of countless diverse, quickly changing stimuli in our environment seemingly without effort. However, doing what our brains do with ease is often an impossible task for computers.

We see, hear and feel, and make sense of countless diverse, quickly changing stimuli in our environment seemingly without effort. However, doing what our brains do with ease is often an impossible task for computers.

Related Articles


Researchers at the Leipzig Max Planck Institute for Human Cognitive and Brain Sciences and the Wellcome Trust Centre for Neuroimaging in London have now developed a mathematical model which could significantly improve the automatic recognition and processing of spoken language. In the future, this kind of algorithms which imitate brain mechanisms could help machines to perceive the world around them. (PLoS Computational Biology, August 14th, 2009)

Many people will have personal experience of how difficult it is for computers to deal with spoken language. For example, people who 'communicate' with automated telephone systems now commonly used by many organisations need a great deal of patience. If you speak just a little too quickly or slowly, if your pronunciation isn’t clear, or if there is background noise, the system often fails to work properly. The reason for this is that until now the computer programs that have been used rely on processes that are particularly sensitive to perturbations. When computers process language, they primarily attempt to recognise characteristic features in the frequencies of the voice in order to recognise words.

"It is likely that the brain uses a different process," says Stefan Kiebel from the Leipzig Max Planck Institute for Human Cognitive and Brain Sciences. The researcher presumes that the analysis of temporal sequences plays an important role in this. "Many perceptual stimuli in our environment could be described as temporal sequences." Music and spoken language, for example, are comprised of sequences of different length which are hierarchically ordered.

According to the scientist’s hypothesis, the brain classifies the various signals from the smallest, fast-changing components (e.g., single sound units like 'e' or 'u') up to big, slow-changing elements (e.g., the topic). The significance of the information at various temporal levels is probably much greater than previously thought for the processing of perceptual stimuli. "The brain permanently searches for temporal structure in the environment in order to deduce what will happen next," the scientist explains. In this way, the brain can, for example, often predict the next sound units based on the slow-changing information. Thus, if the topic of conversation is the hot summer, 'su…' will more likely be the beginning of the word 'sun' than the word 'supper'.

To test this hypothesis, the researchers constructed a mathematical model which was designed to imitate, in a highly simplified manner, the neuronal processes which occur during the comprehension of speech. Neuronal processes were described by algorithms which processed speech at several temporal levels. The model succeeded in processing speech; it recognised individual speech sounds and syllables. In contrast to other artificial speech recognition devices, it was able to process sped-up speech sequences. Furthermore it had the brain’s ability to 'predict' the next speech sound. If a prediction turned out to be wrong because the researchers made an unfamiliar syllable out of the familiar sounds, the model was able to detect the error.

The 'language' with which the model was tested was simplified - it consisted of the four vowels a, e, i and o, which were combined to make 'syllables' consisting of four sounds. "In the first instance we wanted to check whether our general assumption was right," Kiebel explains. With more time and effort, consonants, which are more difficult to differentiate from each other, could be included, and further hierarchical levels for words and sentences could be incorporated alongside individual sounds and syllables. Thus, the model could, in principle, be applied to natural language.

"The crucial point, from a neuroscientific perspective, is that the reactions of the model were similar to what would be observed in the human brain," Stefan Kiebel says. This indicates that the researchers’ model could represent the processes in the brain. At the same time, the model provides new approaches for practical applications in the field of artificial speech recognition.


Story Source:

The above story is based on materials provided by Max-Planck-Gesellschaft. Note: Materials may be edited for content and length.


Journal Reference:

  1. Stefan J. Kiebel, Katharina von Kriegstein, Jean Daunizeau, Karl J. Friston. Recognizing sequences of sequences. PLoS Computational Biology, August 14, 2009; DOI: 10.1371/journal.pcbi.1000464

Cite This Page:

Max-Planck-Gesellschaft. "How Computers Learn To Listen: Scientists Develop Model To Improve Computer Language Recognition." ScienceDaily. ScienceDaily, 16 August 2009. <www.sciencedaily.com/releases/2009/08/090814100103.htm>.
Max-Planck-Gesellschaft. (2009, August 16). How Computers Learn To Listen: Scientists Develop Model To Improve Computer Language Recognition. ScienceDaily. Retrieved March 5, 2015 from www.sciencedaily.com/releases/2009/08/090814100103.htm
Max-Planck-Gesellschaft. "How Computers Learn To Listen: Scientists Develop Model To Improve Computer Language Recognition." ScienceDaily. www.sciencedaily.com/releases/2009/08/090814100103.htm (accessed March 5, 2015).

Share This


More From ScienceDaily



More Mind & Brain News

Thursday, March 5, 2015

Featured Research

from universities, journals, and other organizations


Featured Videos

from AP, Reuters, AFP, and other news services

Former NFL Players Donate Brains to Science

Former NFL Players Donate Brains to Science

Reuters - US Online Video (Mar. 3, 2015) Super Bowl champions Sidney Rice and Steve Weatherford donate their brains, post-mortem, to scientific research into repetitive brain trauma. Jillian Kitchener reports. Video provided by Reuters
Powered by NewsLook.com
Alzheimer's Protein Plaque Found In 20-Year-Olds

Alzheimer's Protein Plaque Found In 20-Year-Olds

Newsy (Mar. 3, 2015) Researchers found an abnormal protein associated with Alzheimer&apos;s disease in the brains of 20-year-olds. Video provided by Newsy
Powered by NewsLook.com
This Nasal Treatment Could Help Ease Migraine Pain

This Nasal Treatment Could Help Ease Migraine Pain

Newsy (Mar. 2, 2015) Researchers gave lidocaine to 112 patients, and about 88 percent of the subjects said they needed less migraine-relief medicine the next day. Video provided by Newsy
Powered by NewsLook.com
How Facebook Use Can Lead To Depression

How Facebook Use Can Lead To Depression

Newsy (Mar. 1, 2015) Margaret Duffy of the University of Missouri talks about her study on the social network and the envy and depression that Facebook use can cause. 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:

Strange & Offbeat Stories


Health & Medicine

Mind & Brain

Living & Well

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