Xperi, the company behind the DTS:X surround sound format, has unveiled a new “Clear Dialogue” audio technology that it says will enable viewers to watch their favourite, noisy shows and sports without needing to rely on subtitles.
The new tech is meant to enhance speech clarity on movies, TVs and sports content, and it does this by using on-device AI algorithms to identify which parts of the audio are speech, and boost them in such a way that they can’t be missed by the viewer. As an on-device technology, the system will be offered to TV manufacturers that want to incorporate it in their new models.
Geir Skaaden, chief products & services officer at Xperi, told reporters at IFA 2024 that one of the most irritating things about watching movies is that, during noisy scenes, you can’t always hear the dialogue between the characters. He explained that this “degrades the quality” of the viewing experience. He also acknowledged that this is the reason why so many people watch movies with the subtitles turned out, but said doing this is more of a workaround, as opposed to a solution.
DTS Clear Dialogue intends to be that real solution, though we should point out that it’s certainly not the first company to introduce dialogue-enhancing technology. Samsung Electronics and Sony have both came up with their own systems, as has Apple with its headsets and earbuds.
However, Xperi seems to think that its years-long experience in sound processing will help it to come up with a superior solution to those rival offerings. The company explained that its device-side AI algorithms process the audio as it comes to the TV via a streaming service, Blu-Ray player or console. It picks up that sound signal, identifying which parts are speech and which are background music and sound effects. Then, it separates the dialogue from the rest of the audio, so it can boost that part while dampening the distractive sounds.
Xperi reckons there should be lots of demand for this, as it cites one of its own surveys that found 84% of consumers have experienced problems in understanding dialogue when watching TV shows and movies.
While many people get around this problem with subtitles, it’s not a perfect solution because that means focusing on the text, which can result in missing some of the details of what’s happening on screen.
With Clear Dialogue, Xperi allows users to manually adjust how the audio is mixed, so they can boost or reduce the dialogue slightly to get the balance just right. As the company points out, this should be useful because everyone’s ears work slightly differently.
Another key feature of DTS Clear Dialogue is that it can function with multiple languages and content genres. As Xperi explains, few companies have really gotten to grips with the “complex problems across languages, content and environments”, and they cannot account for the individuality of each viewer.
“Our device-side AI-based audio processing solution will allow TV OEMs to provide their viewers with the ability to customise and personalise their audio experience," Skaaden said.
A few journalists were lucky enough to get an “ears-on” experience of the new technology, and it has received some good reviews so far, but it remains to be seen if Xperi can popularise the technology. That’s because it will need to work hard to convince not only the TV makers to bake the tech into their next televisions, but also get content providers on board. The likes of Netflix, Disney+ and Amazon Prime Video will all need to provide dedicated support, or else the tech won’t work.
That may be tricky, because currently, Disney+ is the only major streaming provider to support the DTS:X audio technology, and it only started doing so in May. The others all rely on Dolby Atmos sound instead.
To convince TV makers, Xperi said they’ll have flexible integration options, including the option to set aside a dedicated button on their remote controls to adjust dialogue specifically.
While acknowledging these challenges in terms of adoption, Xperi said it’s already looking to support different devices besides TVs.