Community Research and Development Information Service - CORDIS

Sufferers of vocal cord dysfunction regain lost voice with age-appropriate device [Print to PDF] [Print to RTF]

Advances in artificial voice production have led researchers in Finland to develop voice prostheses with improved affective features. For children who have lost their voices, this means the improved artificial voice devices can produce age-appropriate voices, instead of the us...
Sufferers of vocal cord dysfunction regain lost voice with age-appropriate device
Advances in artificial voice production have led researchers in Finland to develop voice prostheses with improved affective features. For children who have lost their voices, this means the improved artificial voice devices can produce age-appropriate voices, instead of the usual voice of an adult male.

The research project, led by Professor Samuli Siltanen, will benefit the 30,000 Finns suffering with vocal cord problems. Professor Siltanen's project is part of the Academy of Finland's Computational Science Research Programme (LASTU).

In the past, one of the fundamental problems of speech signal analysis was finding the vocal cord excitation signal from a digitally recorded speech sound. Another problem was determining the shape of the vocal tract, i.e. the mouth and the throat. This so-called glottal inverse filtering of the speech signal required a highly specialised form of computer calculation. Unfortunately, with traditional techniques inverse filtration was only possible for low-pitch male voices. This meant that replicating the voice of women and children proved difficult because the higher pitch came too close in frequency to the lowest resonance of the vocal tract. However, by adapting the device with new advances in technology and the novel inverse calculation method developed by Siltanen and his team, glottal inverse filtering in these cases has significantly improved.

Vocal cord dysfunction (VCD) is a respiratory disease in which the vocal cords close during breathing. Normally, when breathing in, or inhaling, the vocal cords will open, allowing air to flow into the windpipe (trachea) and reach the lungs. However, with VCD, the vocal cords close together, or constrict, when inhaling. This leaves only a small opening for air to flow into the windpipe and this causes breathing difficulties.

VCD is often associated with acute signs and symptoms of upper airway obstruction, and is commonly mistaken for asthma. It is unknown what exactly causes this problem, but it can be treated, if caught early enough. This involves teaching vocal cord relaxation techniques and deep breathing exercises.

Although VCD can occur in both children and adults, women tend to be more likely to develop it. Possible triggers of VCD are often similar to asthma triggers, hence the misdiagnosis. Triggers may include upper respiratory infections, fumes, odours, cigarette smoke, singing, emotional upset, post-nasal drip and exercise. Sometimes the trigger is not known.

For those with severe vocal cord problems, besides speech synthesis, inverse filtering is also needed in automatic speech recognition. In speech synthesis, a computer will transform text into synthetic speech. The old fashioned way is to record individual words and play them one after the other, but this rarely produces natural-sounding speech.

Professor Siltanen explains: 'Most speech sounds are a result of a specific process. The air flowing between the vocal folds makes them vibrate. This vibration, if we could hear it, would produce a weird buzzing sound. However, as it moves through the vocal tract, that buzz is transformed into some familiar vowel.' The Professor elaborates: 'Singing is a perfect example of this interplay between the vocal cord response and the vocal tract. When we sing the vowel 'a' in different pitches, our vocal tracts remain unchanged but the frequency of the vocal cord excitation changes. On the other hand, we can also sing different vowels in the same pitch, whereby the shape of the tract changes and the excitation stays the same.'

Speech recognition is widely used in mobile phones and automatic telephone services. High-quality glottal inverse filtering improves the success rate of speech recognition in noisy environments.
Source: Academy of Finland

Related information

Countries

  • Finland
Record Number: 35180 / Last updated on: 2012-10-26
Category: Miscellaneous
Provider: EC