Sensors in smartphones may be able to detect how drunk a person is based on changes in their voice, according to a small study. Following experiments involving 18 adults aged 21 and above, scientists said they were able to predict a person’s level of intoxication with 98% accuracy based on an analysis of their voice patterns. Brian Suffoletto, an associate professor of emergency medicine at Stanford University in the US, said the accuracy of the findings of his research “genuinely took me by surprise”. He added: “While we aren’t pioneers in highlighting the changes in speech characteristics during alcohol intoxication, I firmly believe our superior accuracy stems from our application of cutting-edge advancements in signal processing, acoustic analysis, and machine learning.” While Prof Suffoletto said larger studies are needed to confirm the validity of the findings, he added his work has the potential to deliver “just-in-time interventions” to prevent alcohol-related road injuries and deaths in the future. Prof Suffoletto said: “Imagine if we had a tool capable of passively sampling data from an individual as they went about their daily routines and survey for changes that could indicate a drinking episode to know when they need help.” Imagine if we had a tool capable of passively sampling data from an individual as they went about their daily routines and survey for changes that could indicate a drinking episode to know when they need help Prof Brian Suffoletto For the research, published in the Journal of Studies on Alcohol and Drugs, the scientists tailored alcohol doses based on the body weight of each person taking part and were given an hour to finish their drink. Each individual was randomly given a series of tongue twisters to read out loud and a smartphone was used to record their voices. Recordings were made before drinking, and each hour up to seven hours after drinking. The researchers also measured each person’s breath alcohol levels at the beginning of the study and every 30 minutes for up to seven hours. Using digital programmes, the researchers were able isolate the speaker’s voices and analyse measures such as frequency and pitch in one-second increments. When checked against breath alcohol results, the researchers found that the model they developed was a good predictor of how drunk a person was – with 98% accuracy. Prof Suffoletto believes that other behaviours such as gait and texting could be combined with voice pattern sensors to gauge intoxication levels. He said: “Timing is paramount when targeting the optimal moment for receptivity and the relevance of real-time support. “For instance, as someone initiates drinking, a reminder of their consumption limits can be impactful. “However, once they’re significantly intoxicated, the efficacy of such interventions diminishes.” Read More Ireland and Apple await major development in long-running EU tax dispute Guidance urges parents not to buy smartphones for primary school children William ‘blown away’ by futuristic technology from Singapore start-ups Return of original Fortnite map causes record traffic on Virgin Media O2 network NatWest creates new AI-powered chatbot capable of ‘human-like’ conversations Succession star Sarah Snook says AI use in film industry needs ‘stringent rules’

MUNICH & PFORZHEIM, Germany--(BUSINESS WIRE)--May 25, 2023--

By Stephen Nellis CUPERTINO, California Apple on Tuesday unveiled a new iPhone 15 Pro with a titanium case

Mark Zuckerberg was seen sporting rhinestones on his face as he took photos with his family at the concert

Getting control of the use of artificial intelligence is a central issue in the current strikes of Hollywood's actors and writers

Companies including PepsiCo Inc. and Nike Inc. are calling for the European Union to implement stricter emissions targets

The Federal Trade Commission said Wednesday it would appeal a decision from earlier this week by a district court judge allowing Microsoft to close its $69 billion Activision Blizzard merger.

You're about to see people in public tapping two fingers together in the air.

The MSI MAG B760 Tomahawk Wi-Fi ($219.99 MSRP; often $199 or less on sale) is

The US comedian joins two other authors who claim their copyright was infringed to train AI systems.

The news that the data of many users along with app CEO Binderman's emails had been stolen by hackers caused absolute chaos back in 2015

Twitter has added video calling – and left it turned on by default. The feature is now being officially rolled out, Elon Musk confirmed. He said it was an “early version” of a tool he has been hinting at for a year. Video calls are part of Elon Musk’s plans to make Twitter, which he has renamed X, into the “everything app”, offering a wide array of different functionality. For now, video calls are limited to the iOS app, and appear to be rolling out slowly. But they are also switched on by default. The system means that all accounts are liable to receive calls from accounts you follow, or those run by people whose number you have in your address book. To be able to call someone, they must have sent at least one direct message to your account. Users have the option to change that setting, however, either to switch it off or to change who has the ability to make calls. From the direct message settings, users can either disable it entirely or change it so that they can receive calls from people in your address book, from people you follow, or from all “verified” users. Making phone calls is limited to premium subscribers, who pay the monthly subscription for what was once called Twitter Blue. It can be done by opening up the DM menu to start a conversation with someone. If the feature is enabled, then a phone icon should show within the direct message conversation, and tapping audio or video will start the relevant kind of call. Users will receive a notification that they are being called, and will get another telling them they missed the call if they do not pick up. Read More The Twitter app just went very, very strange TikTok prankster Mizzy arrested ‘on suspicion of perverting course of justice’ Study finds ‘deepfakes’ from Ukraine war undermining trust in conflict footage