Section C
Karaoke may never be the same, thanks to research being
presented in Nashville detailing the latest findings in efforts to create a
computerized system that makes average singers sound like
professionals. "Our (26) goal is to have a
computer system that will (27) a poor singing voice into a
great singing voice," said Mark J.T. Smith, a professor of Purdue University,
who is working with a graduate student Matthew Lee to create computer models for
voice analysis and synthesis. These models break the human singing voice into
components that can be (28) to produce a more
professional-sounding rendition (演唱) of the original voice. Far
more work is needed before the system is finished, Smith said. He said the
specialized programs are, however, able to alter certain important (29)
of a person’s voice, such as pitch, duration. Lee
will present the latest research findings during the 145th Meeting of the
Acoustical Society of America in Nashville, Tenn, the nation’s country music
capital. He will (30) the system by playing before-and-after
country music (31) clips to researchers there.
The system uses a special technique to break down the original voice. The
voice is then reconstructed (32) a mathematical method which
enables the system to resynthesize the voice quickly. Smith, who
specializes in signal (33) , began working on the underlying
"sinusoidal mode" (正弦曲线投影模式) in the mid-1980s. (34) . More
recently, Smith and Lee developed a method for modifying to improve the quality
of singing. " (35) , we also face the
challenge of handling all types of voices reliably," Smith said. " (36)