Breaking News! Actually, nothing is breaking so there’s no need to fix it. However, there is something that can give hope to people who have vocal cords which don’t work the way they should. It comes to us from the Fins. Not the fish. The people.
More specifically it’s going on at the Academy of Finland’s Computational Science Research Programme. A group of brainiacs are researching better ways to treat patients that will make better voice prostheses.
Here’s the Straight Story
According to the online journal Science Daily, the news explains:
“For example, for little girls who have lost their voices, the improved artificial voice devices can produce age-appropriate voices, instead of the usual voice of an adult male.”
“One of the fundamental problems of speech signal analysis is to find the vocal cord excitation signal from a digitally recorded speech sound and to determine the shape of the vocal tract, i.e. the mouth and the throat. This so-called glottal inverse filtering of the speech signal requires a highly specialized form of computer calculation. With traditional techniques, inverse filtration is only possible for low-pitch male voices. Women’s and children’s voices are trickier cases as the higher pitch comes too close in frequency to the lowest resonance of the vocal tract. The novel inverse calculation method developed by Siltanen and his team significantly improves glottal inverse filtering in these cases.”
When it comes to synthesizing speech it’s a two-way street. Inverse filtering is required for automatic speech recognition. The computer enters the scene by turning text into synthetic speech. Before, we used to record every single word, playing them one after another.
Think having a conversation with Stephen Hawking. The scientist has anything but natural-sounding speech. Frankly, Hawking actually likes the mechanical, robot-like way he talks.
“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,” explains Siltanen.
Again back to Science Daily.
“Singing, says Siltanen, 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.”
It’s on the horizon. Testing continues. However it could not only help the little girl we spoke of earlier. For instance, speech recognition is all over the place already. Ever make a phone call and the faux-sound on the other end says “Press or say one.” The promise is that super high-quality glottal inverse filtering will make it easier to use your handheld phone (and better for the person on the other end) to actually understand you when you’re in a loud, noisy place.
Original Source: http://austinentmd.com
Image Source: wiki.hill.com/wiki/images/thumb/b/b1/MLG0008-Sound.jpg/300px-MLG0008-Sound.jpg