I have to admit, as cute as Buddy was as a kitten, I don’t miss the “war on sleep” phase.
A woman who adopted a kitten set up a camera to film what happens while she sleeps, like the main characters of the surprisingly scary 2007 film Paranormal Activity, except instead of doors opening and slamming shut by themselves, TVs turning on randomly and other freaky ghost stuff, she got footage of her new kitty gleefully waking her, mostly by belly-flopping on her snoozing human:
I know the experience all too well, and I’d imagine most people who have had a kitten know it too.
Buddy was absolutely ruthless as a baby! He’d scurry into a corner or hide under my desk, wait until I was snoring or just on the cusp of sleep, then climb up and screech the kitten equivalent of “Geronimo!” as he kamikaze’d himself onto my stomach.
Not a fun way to wake up. At all.
Bud would celebrate with delighted trilling, then pad back into the shadows to wait for his next opportunity. Oftentimes I’d hear squeaky little kitten chirps and imagine him laughing as he planned his next attack. He had entirely too much fun torturing me at night.
But fear not, Jenna, it gets better! I’m happy to report the Budster is much sweeter and more considerate as an adult cat. He still wakes me up, but often not to the level of fully awake, and instead of a cat landing a triple lutz, double axle on my stomach, I’m treated to super-soft fur against my face and the calming vibration of the little dude’s purrs.
It might take the better part of a year, but your kitten will chill out, adjust to your sleep schedule and realize a peaceful snooze is more satisfying than nighty games of Harass the Human.
The feline tendency to sit on your face and screech into your ear if your cat’s hungry or really wants your attention? Unfortunately that never goes away…
A while back I wrote a post about MeowTalk, a new app that uses AI — and input from thousands of users sampling their cats’ vocalizations — to translate meows, trills and chirps for the benefit of those of us who don’t fluently speak cat or might need some clarity on what our furry friends are trying to say.
Now that I’ve finally had the opportunity to give MeowTalk a spin, it turns out Bud is a much more polite cat than I thought he was!
What I thought was an unenthusiastic “I acknowledge your presence, human” turned out to be “Nice to see you!” according to MeowTalk.
Buddy’s next meows were “Love me!” and “I love you!”, the app informed me. Weird. I thought he was complaining that I was only half-heartedly simulating prey with his wand toy while watching Jeopardy.
After Jeopardy I headed to the bathroom, which was the real test.
I intentionally closed the door before the little stinker could sneak in the bathroom with me, then held up the phone to capture his muted vocalization. I was sure Bud was saying “Open the door!” but the app told me Buddy was saying “I’m in love!”
Awww. What a good boy. How could I not let him in?
Once inside, Buddy began talking again as I knew he would. He’s a vocal cat.
“I’m looking for love!” the app translated as Bud pawed at the door, demanding to be let back out again. “My love, come find me!”
What was going on here?
Was Bud really professing his undying love for me, his human, or was he workshopping cheesy dialogue for a feline romance novel he’s been secretly working on?
Thankfully, MeowTalk allows you to correct translations if you think the app’s gotten them wrong. This looks more like it:
MeowTalk is in beta, and it can only get better as more users download the app, make profiles for their cats and make an effort to tag vocalizations with their correct meaning.
The app was authored by a software engineer who was part of the team that brought Amazon’s Alexa to life, and the algorithms that power it already show promise: When the app is listening (which it does only actively, after you have explicitly given it permission to do so), it does a great job of distinguishing cat vocalizations from background noise, human chatter, televisions and other incidental sounds. Even my fake meows were unable to fool it.
Each vocalization is sampled and saved to the history tab of your cat’s profile, so you can review and adjust the translations later. If you’ve got more than one cat you can make profiles for each one, and the app says it can tell which cat is talking. I wasn’t able to test this since the King does not allow interlopers in his kingdom, but given MeowTalk’s accuracy in distinguishing meows from every other sound — even with lots of background chatter — I have no reason to doubt it can sort vocalizations by cat.
In some respects it reminds me of Waze, the irreplaceable map and real-time route app famous for saving time and eliminating frustration. I was one of the first to download the app when it launched and found it useless, but when I tried it again a few months later, it steered me past traffic jams and got me to my destination with no fuss.
What was the difference? Few people were using it in those first few days, but as the user base expanded, so did its usefulness.
Like Waze, MeowTalk’s value is in its users, and the data it collects from us. The more cats it hears, the better it’ll become at translating them. If enough of us give it an honest shot, it just may turn out to be the feline equivalent of a universal translator.
And if it’s successful, its creator wants to make a standalone version as a collar, which would translate our cats’ vocalizations in real time. As far as I’m concerned, anything that can help us better understand our cats is a good thing.
It was only a matter of time before someone leveraged machine learning and algorithmic AI to parse cat vocalizations, and thanks to Javier Sanchez, translating your cat’s meows — and trills, huffs and chirps — is now a reality.
Sanchez was a member of Amazon’s machine learning team contributing to the development of Alexa, the now-ubiquitous virtual assistant operated by voice commands.
“I got to see how the sausage was made, how they train their models and work with all the data science platforms,” Sanchez said. “So I was fresh off the heels of that and I was thinking, ‘Well, we could do something similar with cats and it could be an app.’”
Sanchez’s new employers at the tech firm Akvelon saw promise in the idea and gave him the green light.
The resulting app, MeowTalk, is now available on iOS and Android.
There are two layers to the concept: The first one involves nine or 10 “intents” common to all or most cats. They include vocalizations for “Feed me,” “Hey human!”, “Let me out,” and “Pay attention to me,” among others.
Sanchez didn’t guess or intuit the meanings — they’re based on research by a team at the University of Milan, who built a data set of cat vocalizations by attaching tiny microphones to cats and recording everything the fluffsters say. Each feline utterance was analyzed and catalogued by frequency, rhythmic quality and context, among other traits.
The second layer is where it starts to get really interesting: By using MeowTalk like Shazam, the app will start recording your cat’s particular trills, chirps and meows and — with your help — eventually piece together what they mean.
As with dictation software and machine learning in general, the more data the app gets, the better its translations become.
This is important because, while cats share many sounds, each cat develops its own unique vocalizations:
With MeowTalk, you can create a profile for your cat and start using its auto-recognition to translate your cat’s meows and start mapping its language. While some translations are built-in and inherent to the app, translations specific to your cat require you to train the app to recognize your cat’s specific vocabulary and intentions. Translations you deem to be incorrect can be corrected via the app. MeowTalk is not static; instead it learns and evolves with each translation that you confirm, adding to its corpus, just as we would add new words into our own memory banks or language processing programs.
At the same time thousands of other cat owners are also using the app, feeding the algorithm more data, which the app uses to improve itself. Development is ongoing, with future changes reflective of user (and cat) feedback.
“A tool like this can help certain people bond even more with their cats, especially if they can’t be in contact with other people on a regular basis,” Sanchez said. “So this could be a real game changer for a key demographic that have cats.”
Applying what they’re learning via the app, Sanchez and his team are also working toward their next goal: Giving your cat a human voice. They’re developing a small device that clips on a cat’s collar and translates meows into human speech in real time.
That tech has the potential to give me nightmares. Imagine Buddy having a human voice and saying “Gimme snacks now, servant!” “Open the door, butler!” “You’re 23 seconds late with dinner!”
Maybe I’ll pass on the collar device. In the meantime I plan to download the iOS version of MeowTalk and give it a spin. I’ll report back in a week or two after giving it some time to adjust to the Budster. If any of our readers give it a shot, we’d like to hear your impressions as well.
Feline humor, news and stories about the ongoing adventures of Buddy the Cat.