Forget astrology — it turns out that your tone of voice might be more of an indicator of a successful relationship than your Zodiac sign.
Researchers at the University of Utah's USC Viterbi School of Engineering have developed an algorithm that can predict how a romantic relationship will turn out by comparing each member of a couple's voice tone.
To do this, the algorithm analyzes multiple factors, such as pitch, acoustics and vocal intensity, all of which can determine how a relationship will play out. According to the results found in a study published in the journal Proceedings of Interspeech on Sept. 6, when comparing the algorithm's prediction success rate against the more traditional human kind, the former beat out the latter.
The study itself used a sample of 100 different couples, all of whom recorded their conversations and sent them in to the research team. The conversations became the springboard for developing the algorithm.
"What you say is not the only thing that matters, it's very important how you say it. Our study confirms that it holds for a couple's relationship as well," said Utah doctoral student Md Nasir, one of the members of the research team in a press release issued by the university.
After the algorithm was completed, the researchers then assembled a squad of "human experts," each of whom utilized learned behavior codes to make predictions for the selected pool of couples. The team found that the algorithm, not the experts, had a more comprehensive understanding of which couples would make it and which couples wouldn't, all based on objective parsing.
The study and algorithm might help aid therapists, social workers and psychologists in developing new methods of understanding human interconnectivity and interfacing.
"Psychological practitioners and researchers have long known that the way that partners talk about and discuss problems has important implications for the health of their relationships," added team collaborator Brian Baucom. "However, the lack of efficient and reliable tools for measuring the important elements in those conversations has been a major impediment in their widespread clinical use."
Via: Digital Trends
Photo: Cliff | Flickr