New System Can Identify Individual Wolf Howls with 100 Percent Accuracy

A new sound recognition system allows researchers to identify individual wolves by just their howls with perfect accuracy.

Scientists at Nottingham Trent University developed a new code for improved sound analysis which makes it possible for them to distinguish the howls of Eastern gray wolves by the unique pitch and volume in each of their howls.

The technology will be a boon for researchers of wolves as the creatures can have a range of up to 1,000 square miles and cover as many as 30 miles in a day, making them very difficult to track.

"We already knew that wolves, like humans, had distinct voices, and now we are able to identify them with 100% accuracy without ever even seeing them," said researcher Holly Root-Gutteridge.

"In scientific terms this is really exciting, because it means that if we hear a howl on night one we can tell if it is or isn't the same wolf that you hear on subsequent nights."

Root-Gutteridge and her colleagues customized a high-level computational code, specifically for the extraction of howls from recordings of wolves. Wolves generally howl as a form of marking territory, social bonding or communicating with other wolves.

The software proved its worth in tests, able to correctly identify the individual howl of one of 10 wolves after analyzing 67 archive recordings of solo howls. In chorus howls -- in this case the collective howls of 109 individuals -- the system was able to accurately identify the howls of individual wolves 97 percent of the time.

The marks are a significant improvement over previous acoustic identification techniques, which were only accurate 76 percent of the time.

Highly accurate systems for tracking wolves will aid in conservation efforts, the researchers said.

"For the first time we will be able to be sure which wolf is howling to us and track individuals across their territories using just their howls," Root-Gutteridge said. "This is much easier and cost-effective to do than other tracking methods such as GPS-collaring."

The research is published in the journal Bioacoustics