TUNIS, Tunisia, Sept. 9 (UPI) — Researchers in Tunisia say they’ve developed a method of making voice signals clearer for ubiquitous speech recognition systems to understand.
As the recognition systems become commonplace — in computers, at call centers, in airplanes and cars — clear voice input becomes important, a team of scientists at University Campus in Tunis, Tunisia, says.
It could make the difference between a safe maneuver in a car or airplane or an accident, they say.
Cellphone conversations would benefit, and even clandestine recording of speech for security and law enforcement would improve, they say.
“The presence of background noise in speech signal processing constitutes a very serious problem,” the researchers say, explaining it can lead to failed voice commands and errors.
This noise is often referred to as “white noise” and is commonly perceived as random background hiss on a sound recording.
The Tunisia team uses computers to reduce the background noise and has demonstrated the effectiveness of their approach against F16 fighter jet cockpit noise and the noise inside a Volvo car.
“We have applied our hybrid method on several kinds of noises and noisy speech database and the obtained results show an increase in the signal to noise ratio from 5 dB to 12 dB,” the team says.
Copyright 2010 United Press International, Inc. (UPI). Any reproduction, republication, redistribution and/or modification of any UPI content is expressly prohibited without UPI’s prior written consent.