Around the world, there is an increased demand for subtitles. In the UK, for example, the BBC reports that subtitles are primarily intended for viewers with hearing loss, but are used by a wide range of people:About 10% of broadcast viewers regularly use subtitles, rising to 35% for some online content.. Most of these viewers do not have hearing problems.”
Similar trends are taking place around the world for television, social media, and other channels that provide video content.
It is estimated that in Japan, more than 360,000 people are deaf or hard of hearing: 70,000 of them use sign language as their primary form of communication, while the rest prefer written Japanese as the primary way of accessing to content. Furthermore, with almost 30 per cent Of the people in Japan aged 65 and over, the Japan Hearing Aid Industry Association estimates that 14.2 million people have a hearing impairment.
Major Japanese broadcasters have subtitles for most of their programs, which requires a process that includes dedicated staff and the use of specialized equipment worth tens of millions of Japanese yen. “More than 100 local TV stations in Japan face barriers to providing subtitles for live programs due to high equipment cost and staff constraints,” said Muneya Ichise of SI-com. Local stations are of great importance to the communities they serve, and local news programs carry significant updates about the area and its population.
To address this need for accessibility, starting in 2018, YES-com and its parent company, ISCEC Japan, have been testing innovative and cost-effective ways of introducing closed captioning into live broadcasting with local television stations. Their technical solution for delivering captions for live streaming, AI Mimi, is an innovative combination of human input and the power of Microsoft Azure Cognitive Service, creating a more accurate and faster solution through the hybrid format. In addition, ISCEC can make up for the shortage of local captioners by leveraging its own dedicated staff. AI-Mimi has also been presented at the University of Okinawa and innovation was recognized and awarded with a Microsoft AI for Accessibility Grant.
Based on extensive testing and user feedback, related to the need for larger fonts and better display of subtitles on the screen, SI-com can create a model with more than 10 lines of subtitles on the right side of the screen. of the TV, moving away from the most used version with just two lines at the bottom. In December 2021, they demonstrated the technology for the first time, in a live broadcast, in partnership with a local TV channel in Nagasaki.
