Your chances of getting a divorce could be determined by the tone of your voice.
A computer algorithm has been created that predicts whether a couple will have a successful relationship based on how they speak to each other.
In tests, the algorithm predicted which couples would stay together, and which would split up, with nearly 79 per cent accuracy.
In fact, the algorithm did a better job of predicting marital success of couples with serious marital issues than descriptions of the therapy sessions provided by relationship experts.
Researchers, led by Shrikanth Narayanan and Panayiotis Georgiou of the USC Viterbi School of Engineering, recorded hundreds of conversations from more than a hundred couples taken during marriage therapy sessions over two years.
They then tracked their marital status for five years.
From this they developed an algorithm that broke the recordings into acoustic features using speech-processing techniques.
These included pitch, intensity, ‘jitter’ and ‘shimmer’ among many – things like tracking warbles in the voice that can indicate moments of high emotion.
The study did not provide examples or audio recordings of these features and MailOnline has contacted the researchers for specific information.
‘What you say is not the only thing that matters, it’s very important how you say it, the researchers said.
‘Our study confirms that it holds for a couple’s relationship as well.
The team analysed those acoustic features to assess the level of communication within each couple, and they kept track of any change occurring during a single therapy session, or across various sessions.
The way each subject spoke was also assessed in relation to the emotional response it elicited in the other partner.
‘It’s not just about studying your emotions,’ Professor Narayanan said.
‘It’s about studying the impact of what your partner says on your emotions.’
After some tweaks, the program’s assessments were tested against behavioural analyses conducted by human experts.
The team found that studying voice directly yielded more accurate predictions of a couple’s future than the expert’s evaluations.
‘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,’ said Brian Baucom, another researcher from the team.
‘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 ,’ he added.
To improve their algorithm’s predictions, the researchers plan to teach it to factor in other elements, such as body language and the actual meaning of the spoken words.