Your browser is out-of-date!

Update your browser to view this website correctly. Update my browser now


iHeartRadio CPO Says AI Helps Create “Unmatched Digital Listening Experience”

Super Hi-Fi tech will add “perfect transitions,” “sonic leveling” and “gapless playback” to iHeartRadio streams

Earlier this month, iHeartMedia announced it had partnered with artificial intelligence platform Super Hi-Fi to create “intelligent audio transitions” in its iHeartRadio app. The company says the technology will add “perfect transitions,” “sonic leveling” and “gapless playback” to better mimic the experience of live radio.

Radio World’s Brett Moss reached out to iHeartRadio Chief Product Officer Chris Williams to learn more.

Radio World: Exactly what was done?

Chris Williams: iHeartRadio has joined forces with Super Hi-Fi to create an unmatched digital listening experience for our users. We’ve rolled out perfect transitions, sonic leveling and gapless playback for our algorithmically-driven music experiences.

We’re eliminating the periods of silence that users currently experience within streaming music to create an experience that mimics the polished production of live radio. We’ve audited the user experience across all the major services and the average gap is 4-6 seconds between the end of one song and the start of another.

The perception of the gap can be even longer across songs with really long, quiet fades or silence at the end, and this new A.I. takes all this into consideration to create the perfect song transitions just as a seasoned radio programmer or DJ would do.

The technology also seamlessly levels the volume across songs from different decades.

This is important because music plays a role in setting a mood and amplifying an experience. Silence between every song and jarring changes in volume breaks the spell and takes a user out of the flow of their experience. It’s an unwelcome disruption that we can eliminate so that the music does what we intend it to do — enhance the moment.

RW: “Artificial Intelligence” and “AI” are hot phrases these days. How exactly does this qualify as an intelligent activity in comparison to, say, programming song servers to shorten delivery time and making sure MP3/WAV files were uploaded within a select range of loudness or a processor watches the levels?

Williams: To be precise, these are not cross fade or seg tones — the traditional methods the industry uses to try and solve the transition problem. Those “solutions” are fixed based on a length of time (3 second cross-fade) or a static seg tone that doesn’t recognize the sonic attributes of the audio coming up next.

Our solution considers every transition discretely, analyzing the song ending as well as the song playing next. The transition point for a single song is going to vary depending on what track is following, it is dynamic for each unique transition. Our transitions factor in energy, tempo, instrumentation, vocals, processing, volume, production values and hundreds of other attributes for one transition on the fly.

Each time a new song is ingested, the A.I. learns the characteristics of that track and how to best transition it with every other song in the library, similar to the masterful capabilities of our on-air programmers.

RW: Does the artificial intelligence factor into song selection?

Williams: There are two parts of programming that effect the user experience and have to be considered, curation and presentation. The curation, or song selection, is still based on our custom algorithm which is influenced by the curation expertise of our world-class radio programmers. The presentation, or how the songs are stitched together, is what’s being enhanced using the Super Hi-Fi A.I.

RW: How can “artificial intelligence” help a radio operation, or what can it do that people can’t?

Williams: For a streaming music service, it allows us to scale this concept across millions of songs and billions of unique transitions in a way that isn’t possible if it had to be done by hand. We would have to resort to one of the static solutions versus the dynamic approach that we have adopted.

RW: Do you envision a day when iHeartRadio streams will have virtual DJs, complete with Casey Kasem/Gary Owens voices delivering chatter, tidbits about the song/artist or even local weather before the song plays?

Williams: Absolutely. Being able to add in personality, branding, artist messages and weave them all together with the music in a way that is seamless and respects the music is something we are always thinking about.