Show notes
In this episode, Frank and Andy explore voice assistants and the behind the scenes technology that makes them tick.AI Generated Transcript00:00:02 British Voiceover AI LadyHello and welcome to data driven, the podcast where we explore the emerging fields of data science, machine learning and artificial intelligence and will not be the only AI generated voice today. As Frank and Andy interview, my Cousins Alexa, Cortana, Siri and the Google assistant.00:00:18 British Voiceover AI LadyNow that I think of it, the Google assistant needs a proper name.00:00:22 British Voiceover AI LadyDoesn't it?00:00:23 British Voiceover AI LadyWithout further ado, here are your hosts Frank Lavigna and Andy Leonard.00:00:29 FrankSo we're both together and we're going to be talking about voice assistants and kind of how they work and.00:00:38 FrankUh, we have some special guests with us today.00:00:42 FrankWelcome once again, if you're just joining us live. It's Andy later tonight we are here and we are live streaming, data driven podcast where we explore the emerging fields of data science, machine learning an artificial intelligence.00:00:55 FrankHow are you doing Andy?00:00:56 AndyI'm doing pretty good Frank. How are you?00:00:59 FrankI'm doing well. I know you have a hard stop so I won't Yammer too long we have.00:01:04 FrankThree special guests with us today.00:01:06 FrankAnd E 3 three.00:01:09 FrankThat's a record. It is a record.00:01:14 FrankThese guests are.00:01:19 AndyAlexa Hello Alexa.00:01:22 FrankShe's going to say hello back, I'm sure.00:01:26 AndyYeah.00:01:28 FrankCortana.00:01:30 AndyHello Cortana.00:01:33 FrankAnd.00:01:36 FrankOn my phone, I have Google Assistant.00:01:38 AndyHello Google Assistant Hey Google.00:01:41 FrankThat didn't work. It now correctly phones on. Let me tell you whenever there's a training video or like a keynote where they talk about the integration between them. It's pandemonium in my Home Office, because I usually have all three and it's just harder pandemonium.00:01:59 FrankSo I want to switch to, so we're recording this last. If you're watching live. Thank you. If you're watching later, thank you. We always try to respond to the comments. I think we're pretty good about that. And if you're watching this, if you're listening to this on the podcast, I will try to transcribe everything I'm saying. So let me switch.00:02:18 FrankHere.00:02:19 FrankAn I'll see if I can put us in the little bottom here, how do?00:02:22 FrankI do that.00:02:24 FrankThere we go.00:02:27 FrankOh well anyway.00:02:30 AndySo there we.00:02:31 AndyAre were there this is a closed.00:02:34 FrankAlmost there, this is the. This is a quote.00:02:38 FrankFrom Charles the 5th, who if you're not up in your history he was kind of a big deal. I think he was a hapsburg. I don't remember shame on me but he has this quote where he says I speak Spanish to God, Italian to women, French to men in German to my horse.00:02:57 FrankNow you're probably wondering what the heck does this have to do with anything? Well, here's what it has to do with.00:03:03 FrankOh no, PowerPoint is going to crash.00:03:07 FrankNo, you can tell.00:03:08 FrankWe're live here we go. This is what I want to say.00:03:11 FrankThis is the my my modern take on this. I speak to Elexa when I'm home to Cortana. When I'm at work and Google Assistant when I'm in my car or have my phone with me.00:03:24 FrankYou can also replace that with Siri. I don't. I do have an iPad, but it's not with me.00:03:28 AndyThat's Frank, the 1st right.00:03:30 FrankFrank the 1st.00:03:34 FrankI rather like that I rather like that.00:03:38 FrankSo the idea here is you know how do these things work.00:03:41 FrankYou know what?00:03:44 FrankAn you know, in terms of the guests and and kind of things and I know you have a A Time Constraint so I just want to kind of demonstrate something that I've had the chance for a work engagement had a chance to kind of study up on all three because it was a competitive situation between Louis.00:04:03 FrankWhich is ultimately what powers Cortana, kind of behind the scenes, and Lex which is the Alexa version for processing text and dialogue flow, which is the Google version, so it's a lot of mouthfuls an I did. Let's see if we can get our guests to introduce themselves Alexa.00:04:24 FrankHi how are you?00:04:27 Speaker 3I'm feeling like a home run.00:04:29 Speaker 3This weekend I'll be watching a lot of my favorite sports.00:04:35 FrankOK.00:04:38 FrankI'm getting a warning sign on my stream ability here, so I don't know what's going on.00:04:42 AndyWhat's up with that?00:04:43 FrankI don't know Well, you're still hear me so that's a good sign.00:04:46 AndyYeah, you're you're good with me and I'm out here on the in the boondocks with 25 minutes bro.00:04:50 FrankThere you go.00:04:52 FrankHey Cortana.00:04:54 FrankHow are you?00:04:57 Speaker 4Great thanks.00:04:59 FrankThere you go.00:05:00 FrankAnd let's see what our friend Google Assistant.00:05:03 FrankHas to say.00:05:10 FrankHey court, I'm sorry. OK Google, how are you?00:05:18 FrankOops, it's on my Bluetooth, that's why OK.00:05:22 FrankYou could tell where life looks 'cause it's just all bloopers.00:05:27 FrankHow are you?00:05:32 FrankSo we've returned a bunch of short search results, OK?00:05:39 FrankWhat's interesting about these three is that they're all trying to solve essentially the same problem, right? The they they are trying to solve.00:05:46 FrankThe ability to take human language.00:05:49 FrankAnd type, it in and convert it to let me see if I get this screen back up.00:05:55 FrankAn I will maximize that there we go see my fancy setup I do. It's cool, isn't it? Yes.00:06:04 FrankAlright, so ultimately they're all trying to say the same problem. Hey, we have a comment wise guy. Yes I am miserable. OK, alright, so here's the problem that all these devices want to solve, right? This is a human. This is some speaker device thingy.00:06:21 FrankRight?00:06:23 FrankAnd.00:06:25 FrankYou have the cloud.00:06:27 FrankWhich I think is really makes this.00:06:29 FrankPossible in a lot of ways or not. Just possible and practical? Yeah yeah.00:06:34 FrankI say.00:06:36 FrankYou know, turn.00:06:39 FrankI have to be careful 'cause I actually do have the lights in my Home Office so.00:06:43Set up to this.00:06:46 FrankRight, right? So this gets digitized into audio.00:06:51 FrankRight?00:06:52 FrankHere right, I'll draw that by Squiggly Lines.00:06:55 AndyRight, I like to squiggly lines.00:06:57 FrankSee, I'm talented, I'm very.00:06:59 AndyHard you are. You're an artist.00:07:01 FrankThen a cloud service, right? Whether that's Louis.00:07:07 FrankDialogflow00:07:09 FrankOr Lax.00:07:12 FrankConverts that into.00:07:15 FrankBack into text or into text, right? Right turn the.00:07:20 FrankLights on.00:07:27 FrankThen what happens is then you have to figure out what does that mean. What's the context here, right? What's the intent? That's the official word.00:07:34 FrankSo that's turn lights.00:07:38 FrankAnd then on now most people will argue with me. Is that technically this is the intent?00:07:43 FrankAnd this is the the destination or slot.00:07:48 FrankLex calls us a slot and this is the state that you want, right? So ultimately there's 100 different ways I can say that, and this is what makes the really kind of an LP problem, right? Please turn the lights on or do would you kindly turn the lights on right bioshock?00:08:02 FrankRight there for you.00:08:05 FrankUm?00:08:06 FrankThat sort of thing, and then whatever that happens, is that this will then parse that into an action, right?00:08:12 FrankWhich, if you have smart plugs, it will then send a message back through the magic of the Internet and then turn the actual.00:08:20 FrankOh, I like how that's doing that. Turn the actual light on.00:08:27 FrankRight, so that's that's basically solving the same problem.00:08:30 FrankRight?00:08:32 FrankAnd what's interesting about this? I just realized I didn't say it out loud for folks listening on the podcast, but ultimately what happens is my words get translated into an electronic signal, right? A sign? A wave of sorts.00:08:45 FrankAnd then that is then.00:08:47 FrankRe on the other side, it's then sent from the speaker to the cloud, where it will turn those that sound form that sound wave back into text, right? Or words and then it'll go through and it'll parse out.00:09:02 FrankWhat I'm saying is try to get an intent from it or an action to it, and then based on that, some other program that also lives in the cloud.00:09:11 FrankMostly, we'll then take an action based on that. Does that make sense like that? Explain that clearly.00:09:17 AndyI think so yeah, yeah I like it. I like the flow.00:09:21 FrankYeah, and it's it's it's.00:09:22 FrankAmazing how simple this is, right? This is not rocket science inside your average in inside your average you know echo device. You know it's not rocket science, it's just well, this one is the fancy one with the screen, but you know the the typical kind of .1 or whatever is a microphone and speaker in a Wi-Fi connection. It's essentially all it is, right?00:09:42 FrankSo ultimately the the goal then is that let me see if I can D minimize minimize this. So the the goal is is that I have an example of that, and this is essentially a build your own voice kit that I saw at Micro Center for.00:10:01 FrankLike $5 or something like that.00:10:03 FrankAn inside is a speaker, a button, and a Cardboard box.00:10:09 FrankAnd if you attach your Raspberry Pi to this.00:10:12 FrankYou basically have a Google home assistant.00:10:17 AndyThat's nice, yeah.00:10:19 FrankShame on me because I bought this longer ago than I care to admit and I haven't built it yet.00:10:26 FrankBut that's just to demonstrate. The point is that these these actual devices are rather simple in terms of, you know, just them being their own thing, right? So what's interesting about this, and this is where the cutting edge comes is when you when I talk.00:10:41 FrankWe have our human brains or whole.00:10:44 FrankSome will debate about.00:10:45 FrankWhether or not I have a human brain, but let's let's go with you.00:10:49 FrankSo.00:10:51 FrankThe short of it is, is that.00:10:54 FrankI have the ability to understand context right from my previous statement.00:10:58 FrankSo I'm going to mute some of these devices because if I start to hear their name, they'll start going wild. What's interesting is how good Cortana is at this. How good the Google assistant is at this, and how.00:11:14 FrankAlexa needs some room for improvement, right, right? So for instance, if you haven't caught on the shirt I'm wearing says cream cash rules everything around me, that's from a Wu Tang clan song, so I will ask this simple question from Alexa Alexa, who is the Wu Tang clan.00:11:36 Speaker 3According to Wikipedia, Wu Tang clan is an American hip hop group formed in Staten Island, NY city in 1992 original.00:11:45 British Voiceover AI LadyHopes.00:11:46 FrankAlexa.00:11:48 FrankWhat was their first album?00:11:51 Speaker 3According to Wikipedia, the first album is the debut studio album by German dual Modern Talking. It was released on April 1st, 19.00:11:59 Frank80 so you get the idea you and I know like if you asked me who they who the Wu Tang clan were an, then what was their first album? I would tell you right, right?00:12:09 FrankIt does not have the notion of context. This is turns out to be very difficult problem for computers to solve. OK, because.00:12:19 FrankThere's a lot going on, right? So if I start talking to you is like handy. I was at this great restaurant last night that and then we switch to another.00:12:27 FrankTopic.00:12:28 FrankThen00:12:29 FrankWe would, we would then say, Hey where was that place? And then I would kind of know if you said place I would know what you were talking about right? That is humans have trouble with this right? 'cause I have many conversations with my wife that kind of go in different directions 'cause I have no idea where she's talking about.00:12:47 FrankBut I mean it's hard for humans. It's really hard for machines, so let's try and see if Cortana does this any better. Hey Cortana?00:12:54 FrankWho is the Wu Tang clan?00:12:58 Speaker 4According to wikipedia.org Wu Tang, clan is an American hip hop group formed in Staten Island, NY city in 1992. Originally composed of rza.00:13:10 FrankHey Cortana, what was their first album?00:13:15 Speaker 4Should I read a snippet from Wikipedia?00:13:17 Speaker 4That might be related.00:13:19 FrankYeah, I'm afraid.00:13:23 Speaker 4The Wu Tang clan is a NYC based hip hop musical group consisting of 10 American rappers, rza, gza, Method Man, Raekwon, Ghostface Killah.00:13:34 FrankThere's a lot of members of the Wu Tang clan. In case you didn't know.00:13:37 Speaker 4Cappadonna and the label dirty *******00:13:42 FrankHey Cortana, what was their first album?00:13:49 Speaker 4There might be something on Wikipedia.00:13:51 Speaker 4Should I read it?00:13:53 FrankYeah.00:13:56 Speaker 4The Wu Tang clan is a NYC.00:13:58 FrankBased all right?00:13:59 FrankWell, in the past she did get that right.00:14:03 AndyWell, she wasn't completely off base, wasn't completely off. Now she she kept it. Seems like some kind of workflow thing put her into.00:14:11 AndyIt shot well at at least identify the context back to your previous question.00:14:16 FrankIt did on that's a new active. That's a new behavior. I swear I I used to do this demo all the time and depending on the audience it would be Wu Tang clan or you know Aerosmith, you know. So let's see what Google has to say. OK, Google.00:14:32 FrankWho is the Wu Tang clan?00:14:39 FrankAlright, you're not very talkative today.00:14:45 FrankWhat was their first album?00:14:50 FrankOK, the demo gods are not kind to me today.00:14:54 FrankBut in the past this has worked on.00:14:56 FrankOn home assistant, an Cortana.00:15:00 FrankOK, so.00:15:05 FrankSo the reason?00:15:05 FrankWhy we're doing this today, and I know Andy has a hard stop in a couple of minutes is because we are hoping to get data driven as a flash briefing on Alexa.00:15:15 FrankAnd.00:15:17 FrankAlexa.00:15:20 FrankSo I was trying to do this whole surprise thing, but apparently since the demo failed, I figured I'd break into that.00:15:27 FrankInto that, but that's ultimately the goal. But I also think this is an interesting, interesting topic, because for a lot of folks, this is just this magical black box. There is listening, right? An you know it's not magical and it all comes down to math and science, right? An and the key is to understand, kind of how it's built. And once you understand how it's built, you can build your own systems and it's actually not that hard.00:15:47 FrankThere are more moving parts than you would think, but ultimately it just comes down to.00:15:53 FrankYou know you're taking that speed that sound data, converting it into text, then taking that text and then converting that back into some kind of intent in action, right?00:16:04 FrankYeah, and then on the other side, I'm sorry, go ahead.00:16:07 AndyNo, Mark Taylor just said it's a do loop and he's right, he's.00:16:10 FrankA do loop. We have Mark joining us again. Thanks for watching mark.00:16:14 F…
Full show notes at the publisher