TiVo Takes Personalization To The Next Level With Voice ID
The ability to use your voice to interact with smart TVs and streaming media devices is fast becoming the standard. What used to be an exotic and expensive feature is now showing on remote controls microphone buttons for devices that cost only $ 30. Some of the latest smart TVs with built-in far-field microphones do not require a button at all. But as convenient as voice commands are, they’re kind of stupid. All systems try to understand what was said, but few, if any, try to understand who said it, and that creates a great opportunity.
Today, TiVo and Pindrop, a voice authentication company, are taking the first step towards voice commands that understand who is speaking. A new partnership adds Pindrop’s Voice ID technology to TiVo’s voice-enabled devices. Pindrop is also opening up its voice authentication platform so any third party vendor can take advantage of the same features.
But what exactly is this new technology doing and how does it work? Vijay Balasubramaniyan, CEO of Pindrop, gave an overview of Digital Trends.
Being able to identify someone with their voice has many advantages (some of which we will discuss later). In the context of a streaming media platform like TiVo, the biggest benefit is that users can watch movies, TV shows, and other types of content that they most likely want to see.
Many platforms, including TiVo, are already diving very well into the catalogs of your subscribed services such as Netflix, Amazon Prime Video or Disney + and showing you recommended content. Some of these platforms may even create a “Continue Watching” section where you can resume a paused show or move on to the next episode in a season. However, in a sense, these options and recommendations are general. They are based on the activity that all users of that device have performed on a particular device. Depending on the size of your household, this could be many people.
Individual services have already recognized this as an obstacle to accurate personalization, which is why so many now offer the ability to create multiple user profiles. This system works well enough when you navigate using the remote control keypad, but leaves voice-activated interaction without the ability to explain who is watching.
This is where Pindrop comes in. Pindrop’s know-how is based on developing IVR (Interactive Voice Response) services for Fortune 500 companies such as banks, insurance companies and shipping companies. Its technology analyzes more than 250 specific biological and behavioral characteristics of the voice, such as the frequency and harmonics of speech, as well as the patterns of intonation, rhythm and style, which are used to create the equivalent of a vocal fingerprint.
It is similar to voice profiling systems used by Google and Amazon for their respective voice assistants, but unlike these platforms, Pindrop technology can be used with any device.
When you’re using a pindrop-enabled device like a TiVo, voice commands are no longer just verbal replacements for pressing buttons, they’re also a way of understanding who is using the device. The question: “What should I see?” can trigger a range of content suggestions tailored to the speaker rather than the budget. If another member of the household says exactly the same thing, they’ll get completely different results – no profile change required.
Pindrop’s Voice ID system is so sophisticated that its accuracy is not compromised by factors that could otherwise confuse a speech recognition system, such as background noise, changes in a speaker’s voice caused by illness, aging, or even wearing a mask.
There’s even a section of the Pindrop algorithm that can identify a speaker’s tone and emotions. When answering an open-ended question like “What should I see?” A person’s mood can easily affect the content that is offered in the results.
Amazingly – and somewhat frighteningly – Pindrop can also identify multiple voices at the same time. If a person in the room asks for content suggestions and the system hears other voices in the background that it recognizes, it can relay this information to the TiVo platform so that TiVo can make recommendations based on the youngest person in the room (if they so choose) to).
All of this raises several security and privacy issues, but Pindrop claims that how its technology works should allay all concerns. First, the system is opt-in. Before a platform like TiVo uses Pindrop for Voice ID users, those users must explicitly consent to participate. Second, Pindrop says that its voice IDs are not linked to personally identifiable information and that the voice ID data does not include samples of a person’s voice.
Whether or not this voice ID system is popular with smart TV and streaming media device users, Pindrop sees this deployment of its technology as a very early step in a much larger vision for voice authentication.
The aim is to become the voice authentication system for all voice-enabled products, from smartphones to driverless cars. Ultimately, the aim is to provide users with a centrally managed, authorization-based platform on which they can grant and revoke access to devices and services in the same way as you currently use Google to use your Google account to log in to phones, computers etc. can use. and streaming devices.
Once you see the potential of such a far-reaching voice authentication system, it’s amazing that Google, Amazon, and Apple – with their longstanding identity management and voice recognition services – haven’t set their respective flags on area.
Currently, the TiVo implementation of Pindrop technology will serve as a useful test. How well does it work and how seamlessly can voice-based interactions be carried out? We will let you know as soon as we have the opportunity to try it out. TiVo is expected to make Pindrop personalization a feature of its platform in the second quarter of 2021.