Stockholm researchers are building a model of the human voice which could potentially unlock insight to better voice care, talking robots and voice prosthetics.
Three research groups from The KTH Royal Institute of Technology in Stockholm are working with voice and computing experts at universities and research institutes in France, Germany and The Eunison project, which involves physical models and simulated visualizations of the voice.
Using supercomputers, the project involves 3-D physics of the voice, including acoustic output, which may uncover speech technology applications, medical research, pedagogy, linguistics and the arts. The voice model will be operable online, so that researchers anywhere can enter data.
“Our complete model of the human voice will resemble a puppet,” said KTH music acoustics professor Sten Ternström. “The scientist pulls on one or more strings, and then we can see what happens.”
Ternström said that previous voice research efforts have been fragmentary, and that Eunison will be examining an end-to-end look at the voice, combining findings from multiple disciplines.
“The voice is a very complex phenomenon that requires a lot of work to emulate and understand,” said Ternström. “So, we are also interested in how much the model can be simplified, without affecting the voice sounds.”