Explained: How do voice remotes work and why they can be really ‘frustrating’ to use – Times of India

So you have got a new Amazon Fire TV Stick that is Alexa-enabled, which means that simply say “Hey Alexa, play Manchester United football match”. Three to four seconds later, the match will be on. Sounds cool, doesn’t it? If only life with a voice-enabled remote would be that simple. What really happens is that if you say — Hey Alexa, Ok Google, or Hey Siri (if you have the Apple TV) — chances are that it won’t understand properly. You try again and if you speak slowly and clearly, it might just hear you fine. If not, the next command would be an expletive-laden rant about the remote and make you wonder why did you get this remote? Well, it’s not all that bad and we here try to explain how do voice remotes work and what makes them frustrating to use.

How does voice recognition technology work?

Voice or speech recognition technology makes it easy to hands-free control of devices — be it smartphones, speakers, cars or remote controls. While as simple as it may sound — after all it’s just you talking and the device listening — it is vastly complex.
Languages are complicated and even though it may sound you are having a conversation with the remote or a smartphone, in reality it relies so much on machine learning to decipher the correct meaning. What may seem like a rather bizarre analogy but in fact it’s accurate as think of it like speaking to a child. A child can hear what people around her are saying but not really understand it. Parents will keep on talking to the child, give verbal cues, use different pronunciations as she grows up to have a conversation. It may take a good 15-16 years for a child’s vocabulary to fully grow. Voice recognition is very much like that as the more you speak, the the better a remote will understand you.

Simply put, it’s down to pronunciation. As smart and better, voice-based technology is getting, there are far too many accents and pronunciations of the same word that it has to decipher. You must speak slowly and clearly and even if there’s slight background noise, the remote or any other device gets rather confused. It can get frustrating at times but it has come a long, long way since its inception. The Siri of 10 years ago and Siri of now are two different beings. As are Alexa and Google Assistant. Because it’s incredibly complicated yet seems simple is why most people get tend to get frustrated while using them. But do remember that it’s a work in progress. The more you speak to your remote, the better it will get at recognising your voice.