A new computer software programme has the potential to lip-read more accurately than people and to help those with hearing loss, Oxford University researchers have found.
Watch, Attend and Spell (WAS), is a new artificial intelligence (AI) software system that has been developed by Oxford, in collaboration with the company DeepMind.
The AI system uses computer vision and machine learning methods to learn how to lip-read from a dataset made up of more than 5,000 hours of TV footage, gathered from six different programmes including Newsnight, BBC Breakfast and Question Time. The videos contained more than 118,000 sentences in total, and a vocabulary of 17,500 words.
The research team compared the ability of the machine and a human expert to work out what was being said in the silent video by focusing solely on each speaker’s lip movements. They found that the software system was more accurate compared to the professional. The human lip-reader correctly read 12 per cent of words, while the WAS software recognised 50 per cent of the words in the dataset, without error. The machine’s mistakes were small, including things like missing an “s” at the end of a word, or single letter misspellings.
The software could support a number of developments, including helping the hard of hearing to navigate the world around them. Speaking on the tech’s core value, Jesal Vishnuram, Action on Hearing Loss Technology Research Manager, said: ‘Action on Hearing Loss welcomes the development of new technology that helps people who are deaf or have a hearing loss to have better access to television through superior real-time subtitling.
‘It is great to see research being conducted in this area, with new breakthroughs welcomed by Action on Hearing Loss by improving accessibility for people with a hearing loss. AI lip-reading technology would be able to enhance the accuracy and speed of speech-to-text especially in noisy environments and we encourage further research in this area and look forward to seeing new advances being made.’
Commenting on the potential uses for WAS Joon Son Chung, lead-author of the study and a graduate student at Oxford’s Department of Engineering, said: ‘Lip-reading is an impressive and challenging skill, so WAS can hopefully offer support to this task – for example, suggesting hypotheses for professional lip readers to verify using their expertise. There are also a host of other applications, such as dictating instructions to a phone in a noisy environment, dubbing archival silent films, resolving multi-talker simultaneous speech and improving the performance of automated speech recognition in general.’
Learn more: New computer software programme excels at lip reading
[osd_subscribe categories=’artificial-intelligence’ placeholder=’Email Address’ button_text=’Subscribe Now for any new posts on the topic “ARTIFICIAL INTELLIGENCE”‘]
Receive an email update when we add a new ARTIFICIAL INTELLIGENCE article.
The Latest on: Artificial intelligence
[google_news title=”” keyword=”artificial intelligence” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Artificial intelligence
- Powered by OriginTrail, ChatDKG.AI is unlocking a Truly Open Artificial Intelligenceon May 9, 2024 at 11:26 am
Inception program open for application Those looking to build the next big thing with ChatDKG’s trusted AI solution or launch an Initial Paranet Offering are able to submit their application for the ...
- TikTok to start labeling AI-generated content as technology becomes more universalon May 9, 2024 at 10:30 am
TikTok will begin labeling content created using artificial intelligence when it's uploaded from outside its own platform. TikTok says its efforts are an attempt to combat misinformation from being ...
- Artificial intelligence at the root of a real tourism revolution - Part 2on May 9, 2024 at 8:33 am
The tourism sector is constantly evolving as new technologies enter the market. After taking an interest in metaverse, virtual and augmented reality, it's now artificial intelligence's turn to shake ...
- ‘Sic AI’s on each other’ to solve artificial intelligence threat: David Brin, authoron May 9, 2024 at 8:30 am
Best-selling sci-fi author David Brin says AIs could be made to police each other under threat of losing blockchain-based registration.
- Explainer: How dependent is China on US artificial intelligence technology?on May 9, 2024 at 7:29 am
The Biden administration plans to put guardrails on U.S.-developed artificial intelligence (AI) models that power popular chatbots like ChatGPT to safeguard the technology from countries such as China ...
- Artificial Intelligence ‘Friends’on May 9, 2024 at 3:48 am
Artificial intelligence, we are told, is a transformative economic force; it will change workers’ jobs, boost corporate profits and reshape industries. But for the last month, I’ve been investigating ...
- Elon Musk’s Artificial Intelligence Startup xAI Reportedly Nears $18 Billion Valuation With Fresh Funding As AI Race Heats Upon May 9, 2024 at 3:03 am
The funding would provide Musk’s venture, which is behind the Grok AI chatbot, a welcome boost in its efforts to catch up to AI rivals like OpenAI, Google and Anthropic.
- Department of Homeland Security pilots new Artificial Intelligence program for immigration processon May 9, 2024 at 2:10 am
The program seeks to train officers to review applicants for refugee states in the U.S.. The machine would not make asylum decisions.
- 2 Millionaire-Maker Artificial Intelligence (AI) Stockson May 9, 2024 at 1:55 am
Snowflake ( SNOW -0.82%) and Super Micro Computer ( SMCI 0.41%) have become pivotal in the development and growth of artificial intelligence (AI) technology. These stocks have the ingredients to ...
via Bing News