Categories
Life hack

How to train siri cortana and google to understand your voice better

Chris Hoffman
How to train siri cortana and google to understand your voice betterChris Hoffman
Editor-in-Chief

Chris Hoffman is Editor-in-Chief of How-To Geek. He’s written about technology for over a decade and was a PCWorld columnist for two years. Chris has written for The New York Times, been interviewed as a technology expert on TV stations like Miami’s NBC 6, and had his work covered by news outlets like the BBC. Since 2011, Chris has written over 2,000 articles that have been read nearly one billion times—and that’s just here at How-To Geek. Read more.

How to train siri cortana and google to understand your voice better

No two people sound exactly alike. Different people have different accents and ways of pronouncing words, and computer voice recognition systems like Siri, Cortana, and Google’s voice search aren’t as good as actual human beings at understanding every voice. Train your voice assistant and it’ll be better at understanding you.

Traditionally, computerized voice recognition systems have required some training before they understood you. Modern voice assistants are designed to “just work,” but you can still make them recognize the words you say more often by training them.

Siri on iOS 9

Apple added some voice training features to Siri in iOS 9. Activate the “Hey Siri” feature — which allows you to say “Hey Siri” and start talking to Siri from anywhere — and you’ll be prompted to perform some voice training.

(On most iPhones, this only works while your screen is on or while your phone is plugged in. If you have an iPhone 6s, you can also say “Hey Siri” while your screen is off to start a voice search.)

To activate this feature, open the Settings app on your iPhone or iPad, tap the “General” category, and tap “Siri.” Activate the “Allow “Hey Siri”” option and you’ll be prompted to train Siri.

Siri will have you say “Hey Siri”, “Hey Siri, how’s the weather today?”, and “Hey Siri, it’s me.” This will improve Siri’s ability to understand you.

How to train siri cortana and google to understand your voice better

Cortana on Windows 10

Cortana includes a voice-training feature so you can help Cortana understand your voice better. Like Google, Cortana will upload your voice activity and store it to help Cortana learn your voice over time and understand you better — that’s what the “Speech, inking, & typing” privacy setting controls. You could disable it and tell Cortana to “Stop getting to know me,” but then it would have a harder time understanding you.

To start training Cortana, click or tap the Cortana bar on the taskbar, click the “Notebook” icon at the left of the Cortana pane, and select “Settings.” Activate the “Let Cortana respond to “Hey Cortana” option and then click the “Learn my voice” button. Cortana will walk you through saying a variety of phrases to learn your voice. All of these are things you can actually do with Cortana.

How to train siri cortana and google to understand your voice better

Google on Android, Chrome, and Elsewhere

Google doesn’t include a special training process on Android. However, some manufacturers do offer this feature on their devices. For example, the Moto Voice application on Motorola phones will prompt you to train it by saying several things the first time you open the Moto Voice app.

Instead, Google captures and keeps all the voice searches, voice actions, and voice dictation activities you perform on your phone. It stores this with your “Voice and Audio Activity,” which is tied to your Google account and used on Android, in Chrome, and in Google’s apps on iOS. You’re free to delete or halt collection of this information at any time, but leaving it enabled means Google will learn how to recognize your voice and the way you pronounce words over time.

To choose whether or not your Android device reports this information, use the “Activity controls” pane in the Google Settings app.

How to train siri cortana and google to understand your voice better

None of these training processes are mandatory, but they’ll help the service in question understand you better. If you find yourself annoyed that your phone, tablet, or computer doesn’t understand you as well as it should, it may just need some training.

Other similar programs — for example, speech-to-text programs — generally have their own integrated training features, too. For example, the Speech Recognition feature that’s been part of Windows for years can be trained to work better.

  • › How to Add Images to Questions in Google Forms
  • › How to Delete Your Photos on Facebook
  • › Razer Thinks You Want a PC Gaming Headset That Vibrates
  • › How to Get a Link to a Photo or Video on Instagram
  • › The Fix for Slow AMD Processors on Windows 11 Is Here

How to train siri cortana and google to understand your voice better Chris Hoffman
Chris Hoffman is Editor-in-Chief of How-To Geek. He’s written about technology for over a decade and was a PCWorld columnist for two years. Chris has written for The New York Times, been interviewed as a technology expert on TV stations like Miami’s NBC 6, and had his work covered by news outlets like the BBC. Since 2011, Chris has written over 2,000 articles that have been read nearly one billion times—and that’s just here at How-To Geek.
Read Full Bio »

How to train siri cortana and google to understand your voice better

If you don’t know, Cortana is a virtual assistant created by the Microsoft Corporation integrated with the Windows 10 OS. In simple terms, it is just a variation of the Siri on iOS, and Google Assistant on Android smartphones.

There are plenty of things you can do with Cortana. For example, you can create reminders, control the smart bulbs and lights, weather forecasts, map directions, play music, add calendar events, look up new words while browsing the web, open Windows 10 apps etc.

Additionally, Cortana on your PC can alert you whenever you miss a call on your phone. To use this feature, you’ll need the Cortana app on an Android or Windows phone.

Cortana does things for you by listening to your voice. But for it to understand your voice and what you are saying, you should train it. In this article, we are going to look into the steps for training Cortana in Windows 10 so that you won’t have to repeat yourself.

Steps to Train Cortana in Windows 10

  1. Open Cortana by pressing Win+S buttons together.
  2. Click on the Notebook icon at the left side.
  3. Click on Settings.
  4. Click on Learn my voice button.
  5. Click on the Start button.
  6. Follow the on-screen instructions and speak the sentences provided to train Cortana.

While training Cortana, make sure that you speak loud and in your natural tone so that Cortana will understand you whenever you instruct it to do something. Do not try to make up your voice or speak unnaturally.

If you make up your voice, you may complete the training for the Cortana, however, once you speak in your natural tone, Cortana will find it difficult to understand what you want. So, you will be forced to repeat the same thing multiple times to make Cortana listen to you.

That’s all for now. Please leave your feedback in the comment section below.

How to train siri cortana and google to understand your voice better

One of the new features in Windows 10, which was ported from Windows Phone, is the digital assistant Cortana. Here’s how to make it understand you better.

One of the new features in Windows 10, which was ported from Windows Phone, is the digital assistant Cortana. It works fairly well out of the box without any training. But if you want better results from Cortana, take a few minutes and train it to recognize your voice.

The reason you would want to do this is if you have the “Hey Cortana” feature enabled. Cortana, like digital assistants on other platforms, can do a lot of things for you such as create reminders, open apps or settings, provide sports scores and weather forecasts, and a lot more.

In fact, Cortana gets more capabilities through updates on a regular basis. And the better Cortana understands you, the smarter it gets.

Train Cortana Learn Your Voice

First, make sure you have “Hey Cortana” turned on by going to Notebook > Settings. And when you do that, ensure that it’s set to Respond best to me.

Then just underneath that, select the Relearn my voice button.

How to train siri cortana and google to understand your voice better

A wizard will start, and you’ll need to go through and repeat six phrases that Cortana reads to you.

How to train siri cortana and google to understand your voice better

These phrases are all things you can ask Cortana and will help it get more familiar with your voice. Make sure you’re in a quiet room without anything playing in the background like music or your TV.

Of course, everyone’s voice is different, and this helps the AI that powers Cortana to become more familiar with your pitch and vocal inflections. I do this on all of my Windows 10 devices, and when reading the phrases, just speak naturally like you normally would.

When complete, Cortana will understand you better and will be able to respond faster and more accurately.

Don’t be loud and over enunciate the phrases. That way you can speak like normal and get the information you want…just like in Star Trek!

How to train siri cortana and google to understand your voice better

For more on the Windows 10 digital assistant, check out our collection of Cortana articles. And, for detailed discussion, join up with our Windows 10 Forums.

How to train siri cortana and google to understand your voice better

Kaksi ihmistä ei kuulu täsmälleen samaan. Eri ihmisillä on erilainen aksentti ja sananvapaus, ja tietokoneen äänentunnistusjärjestelmät, kuten Siri, Cortana ja Googlen äänihaku eivät ole yhtä hyviä kuin todelliset ihmiset ymmärtävät jokaisen äänen. Harjoittele avustajasi ja se on parempi ymmärtää sinua.

Perinteisesti tietokoneohjatut äänentunnistusjärjestelmät ovat vaatineet koulutusta ennen kuin he ymmärtävät teidät. Nykyaikaiset äänioperaattorit on suunniteltu "vain työskentelemään", mutta voit silti tehdä niistä tunnistettavia sanoja useammin kouluttamalla niitä.

Siri iOS 9: lla

Apple lisäsi joitain äänikoulutusominaisuuksia Siriille iOS 9: ssä. Aktivoi Hey Siri -ominaisuus – jonka avulla voit sanoa "Hey Siri" ja aloittaa puhumisen Sirin kanssa mistä tahansa – ja sinua kehotetaan suorittamaan jonkin äänikoulutuksen.

(Useimmissa iPhonissa tämä toimii vain, kun näyttö on päällä tai puhelimen ollessa kytkettynä. Jos sinulla on iPhone 6s, voit myös sanoa "Hei Siri", kun näyttö on pois päältä aloittaaksesi äänihakun.)

Ota tämä ominaisuus käyttöön avaamalla Asetukset-sovellus iPhonellasi tai iPadillasi, napauta "Yleinen" -luokka ja napauta "Siri". Aktivoi "Salli" Hei Siri "-vaihtoehto ja sinua kehotetaan kouluttamaan Siri.

How to train siri cortana and google to understand your voice better

Cortana Windows 10: ssä

Cortanaan kuuluu äänikoulutusominaisuus, jonka avulla voit auttaa Cortanaa ymmärtämään äänesi paremmin. Kuten Google, Cortana lataa äänitoiminnot ja tallentaa sen, jotta Cortana osaa oppia ääniasi ajan kuluessa ja ymmärtää paremmin – niin "Puhe, inking & typing" -asetus ohjaa. Voit poistaa sen käytöstä ja kertoa Cortanalle "Älä tunne minua", mutta silloin olisi vaikeampaa ymmärtää sinua.

Jos haluat aloittaa Cortan-harjoittelun, napsauta tai napauta tehtäväpalkin Cortana-palkkia, napsauta Cortanan ruudun vasemmalla puolella olevaa "Notebook" -kuvaketta ja valitse "Asetukset". Aktivoi "Anna Cortanan vastaus Hey Cortanaan" ja valitse sitten "Opi ääneni" -painiketta. Cortana vie sinut sanomaan monenlaisia ​​lauseita oppimaan äänesi. Kaikki nämä ovat asioita, joita voit todella tehdä Cortanan kanssa.

How to train siri cortana and google to understand your voice better

Google Androidissa, Chromessa ja muualla

Google ei sisällä erityistä koulutusprosessia Androidissa. Jotkut valmistajat tarjoavat kuitenkin tämän ominaisuuden laitteilleen. Esimerkiksi Moto Voice -sovellus Motorola-puhelimissa kehottaa sinua kouluttamaan sitä sanomalla useita asioita ensimmäistä kertaa, kun avaat Moto Voice -sovelluksen.

Sen sijaan Google kaappaa ja pitää kaikki puhelimesi suorittamat äänihaku-, äänitoiminnot ja äänikomentotoiminnot. Se tallentaa tämän "Voice and Audio Activity" -ohjelmalla, joka on sidottu Google-tiliisi ja jota käytetään Androidissa, Chromessa ja Googlen sovelluksissa iOS: ssä. Voit vapaasti poistaa tai pysäyttää näiden tietojen keräämisen milloin tahansa. Jäljelle jääminen mahdollistaa sen, että Google oppii tunnistamaan äänesi ja tapa, jolla sanot sanat ajan mittaan.

Jos haluat, että Android-laite ilmoittaa nämä tiedot, käytä Google-asetukset -sovelluksen Toiminto-valvonta-paneelia.

How to train siri cortana and google to understand your voice better

Kukaan näistä koulutusprosesseista ei ole pakollinen, mutta ne auttavat kyseistä palvelua ymmärtämään sinua paremmin. Jos huomaat, että puhelin, tabletti tai tietokone ei ymmärrä sinua niin hyvin kuin mahdollista, se saattaa tarvita vain jonkin verran koulutusta.

Muut samankaltaiset ohjelmat – esimerkiksi puheen ja tekstin ohjelmat – sisältävät yleensä myös omat integroidut koulutusominaisuudet. Esimerkiksi Puheentunnistus-ominaisuus, joka on ollut osa Windowsia vuosia, voidaan kouluttaa paremmin toimimaan.

How to train siri cortana and google to understand your voice better

Žádné dva lidé nezněly přesně stejně. Různí lidé mají různé akcenty a způsoby vyslovování slov a počítačové systémy pro rozpoznávání hlasu, jako je Siri, Cortana a hlasové vyhledávání Google, nejsou tak dobré jako skutečné lidské bytosti při porozumění každému hlasu. Trénujte svého hlasového asistenta a je lepší, abyste vás pochopil.

Tradičně počítačové systémy pro rozpoznávání hlasu vyžadovaly nějaký výcvik, než vás pochopili. Moderní hlasové asistenty jsou navrženi tak, aby “pracovali jen”, ale stále je můžete rozpoznat slova, která se vám vyskytují častěji, když je trénujete.

Siri na iOS 9

SOUVISEJÍCÍ: Naučte se používat Siri Handy iPhone Assistant

Apple přidal některé funkce hlasového výcviku do Siri v systému iOS 9. Aktivujte funkci “Hey Siri” – což vám umožní říct “Hej Siri” a začněte mluvit se Siri odkudkoli – a budete vyzváni

(U většiny telefonů iPhone funguje pouze v době, kdy je vaše obrazovka zapnutá nebo když je telefon připojen. Pokud máte iPhone 6s, můžete také říct “Hey Siri”, když je obrazovka vypnutá spusťte hlasové vyhledávání.)

Chcete-li tuto funkci aktivovat, otevřete v iPhonu nebo iPadu aplikaci Nastavení, klepněte na kategorii “Obecné” a klepněte na “Siri.” Aktivujte volbu “Allow” Hey Siri ” budete vyzváni k trenérství Siriho

Siri vás bude říkat “Hej Siri”, “Hej Siri, jak to je počasí dnes?” a “Hej Siri, to jsem já.”

How to train siri cortana and google to understand your voice better

Cortana na Windows 10

SOUVISEJÍCÍ: 15 věcí, které můžete dělat s Cortanou na Windows 10

Cortana obsahuje funkci hlasového výcviku, abyste Cortanu mohli pomoci pochopit. váš hlas lépe. Stejně jako Google vám Cortana nahraje vaši hlasovou aktivitu a uloží ji tak, aby pomohla Cortaně dozvědět váš hlas v průběhu času a pochopit vás lépe – to je to, co řídí nastavení ochrany soukromí “Řeč, inkoust a psaní”. Mohli byste ji vypnout a říct Cortaně, že “přestanete mě poznat”, ale pak by to bylo těžší pochopit.

Chcete-li začít trénovat Cortanu, klepněte nebo klepněte na panel Cortana na hlavním panelu, klepněte na tlačítko “Notebook” ikonu na levé straně podokna Cortana a vyberte “Nastavení”. Aktivujte funkci “Nechte Cortanu odpovědět na otázku” Hey Cortana “a klikněte na tlačítko” Naučit můj hlas “. Cortana vás povede různými frázemi, abyste se naučili svůj hlas. Všechno je to, co můžete vlastně dělat s Cortanou.

How to train siri cortana and google to understand your voice better

Google v systému Android, Chrome a jinde

SOUVISEJÍCÍ: 16 Akce Android Voice, aby Android byl váš osobní osobní asistent

Google nezahrnuje speciální tréninkový proces na platformě Android. Někteří výrobci nabízejí tuto funkci na svých zařízeních. Například aplikace Moto Voice na telefonech Motorola vás vyzve k tomu, abyste se naučili tím, že při prvním otevření aplikace Moto Voice vysvětlíte několik věcí.

Místo toho Google zachycuje a uchovává všechna hlasová vyhledávání, hlasové akce a diktování hlasu činnosti, které provádíte v telefonu. Uchovává to s vaší “hlasovou a zvukovou aktivitou”, která je svázána s vaším účtem Google a používá se v systému Android, v prohlížeči Chrome a v aplikacích Google v systému iOS. Můžete kdykoli vymazat nebo zastavit sběr těchto informací, ale ponecháte-li to zapnuté, znamená to, že Google se dozví, jak rozpoznat váš hlas a způsob, jakým budete v průběhu času vyslovovat slova.

Chcete-li zvolit, zda se vaše zařízení Android hlásí tyto informace použijte podokno “Ovládací prvky činnosti” v aplikaci Nastavení Google.

How to train siri cortana and google to understand your voice better

Žádný z těchto tréninkových procesů není povinný, ale pomohou vám tuto službu lépe porozumět. Pokud se vám zdá, že váš telefon, tablet nebo počítač vás nerozumí stejně dobře, může potřebovat pouze nějaký výcvik.

Jiné podobné programy – například programy řeči do textu – obecně mají jejich vlastní integrované tréninkové funkce. Funkce rozpoznávání řeči, která je již řadu let součástí systému Windows, může být vyškolena k lepší práci.

How to train siri cortana and google to understand your voice better

Skenery otisku prstů byly na některých modelech notebooků po dobu přibližně tak dlouho, dokud existoval koncept, ale vždy byly obvykle jakýsi podivný a nezapomenutelný. Poté přichází Apple, který to nejen vylepšuje, ale je to nezbytnou funkcí. Apple představil Touch ID s iPhone 5S v roce 2013 a rychle se osvědčil jako nepostradatelná vlastnost.

How to train siri cortana and google to understand your voice better

Systém Windows obsahuje různé vizuální efekty a animace, díky nimž se operační systém cítí trochu přátelštější. Dobrým příkladem je animace, která zmizí nebo sklouzne do menu několik sta milisekund po kliknutí na ně. Přizpůsobení tohoto zpoždění se však může stát, že se vaše PC bude cítit trochu snappier.

How to train siri cortana and google to understand your voice better

Žádní dva lidé nejsou úplně stejní. Různí lidé mají různé akcenty a způsoby vyslovování slov a počítačové systémy pro rozpoznávání hlasu, jako je Siri, Cortana a hlasové vyhledávání Google, nejsou tak dobré jako skutečné lidské bytosti při porozumění každému hlasu. Trénujte svého hlasového asistenta a bude lepší, abyste vás pochopil.

Tradičně počítačové systémy pro rozpoznávání hlasu vyžadovaly nějaký výcvik, než vás pochopili. Moderní hlasové asistenty jsou navrženy tak, aby "fungovaly jen", ale stále je můžete rozpoznat slova, která říkáte častěji výcvikem.

Siri na iOS 9

Apple přidal některé funkce hlasového výcviku do Siri v systému iOS 9. Aktivujte funkci "Hey Siri" – což vám umožní říct "Hej Siri" a začněte s Siriho povídat odkudkoli – a budete vyzváni k provedení nějakého hlasového výcviku.

(Na většině telefonů iPhone to funguje pouze v době, kdy je obrazovka zapnutá nebo je telefon připojen. Pokud máte iPhone 6s, můžete také spustit "Hey Siri", když je obrazovka vypnutá, abyste zahájili hlasové vyhledávání.)

Chcete-li tuto funkci aktivovat, otevřete v iPhonu nebo iPadu aplikaci Nastavení, klepněte na kategorii "Obecné" a klepněte na "Siri". Aktivujte možnost "Povolit" Hej Siri "a budete vyzváni k školení Siri.

Siri vás bude říkat "Hej Siri", "Hej Siri, jak to je počasí dnes?" A "Hej Siri, to jsem já." To zlepší Siriho schopnost porozumět vám.

How to train siri cortana and google to understand your voice better

Cortana v systému Windows 10

Cortana obsahuje funkci hlasového výcviku, abyste Cortanu mohli lépe porozumět vašemu hlasu. Stejně jako Google vám Cortana nahraje vaši hlasovou aktivitu a uloží ji tak, aby pomohla Cortaně dozvědět váš hlas v průběhu času a lépe vám porozumět – to je to, co řídí nastavení ochrany soukromí "Řeč, inkoust a psaní". Mohl byste to vypnout a říct Cortaně, že "přestanete mě poznat," ale pak by to bylo těžší pochopit.

Chcete-li spustit výcvik Cortany, klepněte nebo klepněte na panel Cortana na hlavním panelu, klepněte na ikonu "Notebook" na levé straně podokna Cortana a vyberte "Settings". Aktivujte "Let Cortana odpovědět na" Hey Cortana " tlačítko "Naučit můj hlas". Cortana vás povede různými frázemi, abyste se naučili svůj hlas. Všechno to jsou věci, které můžete s Cortanou skutečně dělat.

How to train siri cortana and google to understand your voice better

Google v systému Android, Chrome a jinde

Společnost Google nezahrnuje speciální tréninkový proces v systému Android. Někteří výrobci nabízejí tuto funkci na svých zařízeních. Aplikace Moto Voice na telefonech Motorola vás například vyzve k tomu, abyste v první příležitosti otevření aplikace Moto Voice vyzkoušeli několik věcí.

Místo toho Google zachycuje a udržuje všechny hlasové vyhledávání, hlasové akce a hlasové diktátové aktivity, které provádíte v telefonu. Uchovává to s vaší "hlasovou a zvukovou aktivitou", která je svázána s vaším účtem Google a používá se v systému Android, v prohlížeči Chrome a v aplikacích Google v systému iOS. Můžete bezplatně smazat nebo zastavit shromažďování těchto informací, ale ponecháte-li to zapnuté, znamená to, že Google se dozví, jak rozpoznat váš hlas a způsob, jakým v průběhu času vyslovujete slova.

Chcete-li zvolit, zda má zařízení Android hlásit tyto informace, použijte podokno "Ovládací prvky činnosti" v aplikaci Nastavení Google.

How to train siri cortana and google to understand your voice better

Žádný z těchto tréninkových procesů není povinný, ale pomohou vám tuto službu lépe porozumět. Pokud zjistíte, že váš telefon, tablet nebo počítač vás nerozumí stejně dobře, může to trvat jen potřeba školení.

Jiné podobné programy – například programy řeči – text – mají také své vlastní integrované tréninkové funkce. Funkce rozpoznávání řeči, která je součástí systému Windows již řadu let, může být například vyškolena k lepší práci.

Voice assistants changed the way we interact with technology. Why set an alarm manually when Alexa can do it for you? Siri can type up your emails.

That’s all well and good — until the third time in a row, your AI assistant is confused and you’re frustrated.

If you’ve been having a hard time getting through to your voice assistant, here’s how to get Alexa, Siri, and Google Assistant to understand you better.

How to train siri cortana and google to understand your voice better

Speak to Alexa, Google or Siri like you’re talking to a friend. (iStock)

1. Watch your tone

You’ve probably seen viral videos of people screaming at Alexa or Google Assistant when they don’t get through the first time. While it’s tempting to let out your frustration that way, yelling at any voice assistant makes it even less likely to understand you.

For optimal results, talk at a normal volume. Speak to Alexa, Google or Siri like you’re talking to a friend.

2. Don’t block the mic

You ask Siri a question, and you don’t get an answer. Surprise, your thumb is blocking the mic. If your voice assistant can’t hear you, make sure you’re not the problem.

With Google Assistant and Amazon Alexa, you need proper clearance. Amazon suggests at least eight inches of space around your Echo device. That isn’t always possible, but a little breathing room helps it pick up your words more accurately.

How to train siri cortana and google to understand your voice better

Amazon Echo devices. (Reuters)

3. Act natural

Are you one of those people who talk to a voice assistant robotically? I get it. You think since you’re talking to a robot, you should sound like one too. But today’s AI is designed to pick up on regular human speech.

Talk like a normal person, and your voice assistant will respond best. Instead of “Alexa, alarm 7!” say, “Alexa, set an alarm for 7 in the morning.”

4. Create profiles for various family members

You can train Amazon’s Alexa to recognize up to six different people. This tip can be handy if you have family members with foreign accents or children at varying levels of language development. It’s an easy process and you can let Alexa slowly adjust to various voices.

Here’s how to set up Alexa profiles:

  • Open the Alexa app.
  • Tap More > Settings.
  • Select Your Profile.
  • Next to Voice, select Create.
  • Select Continue.

You can also train Siri to recognize your voice. Take this extra step if you have an accent or speak quickly. You likely did this when you set up your phone, but try again if you and Siri aren’t getting along.

  • Open Settings on your iPhone.
  • Click on Siri & Search.
  • Toggle the switch next to Listen for “Hey Siri” off and back on.
  • Complete the on-screen setup process to train Siri to recognize your voice.

You can also teach Siri how to pronounce the names of people in your life, so you call the right person. If Siri says a name wrong, say, “You pronounced it wrong” to set the smart assistant straight.

How to train siri cortana and google to understand your voice better

Google Home Hub is one of the company’s devices that offers Google Assistant. (AP)

Google Assistant has a similar feature called Voice Match. You can teach Google Assistant how to recognize your commands more accurately.

  • Open the Google Home app.
  • Tap your profile picture or initials.
  • Head to Assistant settings > Voice Match.
  • Click Add Devices.
  • Follow the on-screen directions.

5. Make your smart assistant smarter

Often, Alexa, Google Assistant, or Siri will ask for clarification about something you said. This can be annoying, but answering will help train the AI to know you better.

When you respond to clarify what you were asking about in the first place, it shows your smart assistant how to do better in the future. Every clarification you make, your AI technology remembers and adapts to, making it less likely for you to have to repeat yourself next time.

There are, however, some questions and settings that might be worth the annoyance. Tap or click for fixes to 5 irritating Echo settings.

Check out my podcast “Kim Komando Explains” on Apple, Google Podcasts, or your favorite podcast player.

ProPublica obtained IRS information showing how billionaires like Jeff Bezos, Elon Musk and Warren Buffett pay little in income tax when compared to their massive wealth — sometimes, even nothing. I sat down with an experienced tax accountant who works with wealthy clients to get the scoop. Plus, we talked about special tax credits to lower your taxes.

What digital lifestyle questions do you have? Call Kim’s national radio show and tap or click here to find it on your local radio station. You can listen to or watch The Kim Komando Show on your phone, tablet, television, or computer. Or tap or click here for Kim’s free podcasts.

CLOSE

How to train siri cortana and google to understand your voice better

Watch your tone! Yelling at any voice assistant makes it even less likely to understand you. (Photo: Getty Images)

Voice assistants changed the way we interact with technology. Why set an alarm manually when Alexa can do it for you? Siri can type up your emails.

That’s all well and good – until the third time in a row, your artificial intelligence assistant is confused and you’re frustrated.

If you’ve been having a hard time getting through to your voice assistant, here’s how to get Alexa, Siri, and Google Assistant to understand you better:

1. Watch your tone

You’ve probably seen viral videos of people screaming at Alexa or Google Assistant when they don’t get through the first time. While it’s tempting to let out your frustration that way, yelling at any voice assistant makes it even less likely to understand you.

For optimal results, talk at a normal volume. Speak to Alexa, Google, or Siri like you’re talking to a friend.

2. Don’t block the mic

You ask Siri a question, and you don’t get an answer. Surprise, your thumb is blocking the mic. If your voice assistant can’t hear you, make sure you’re not the problem.

With Google Assistant and Amazon Alexa, you need proper clearance. Amazon suggests at least 8 inches of space around your Echo device. That isn’t always possible, but a little breathing room helps it pick up your words more accurately.

3. Act natural

Are you one of those people who talk to a voice assistant robotically? I get it. You think since you’re talking to a robot, you should sound like one, too. But today’s AI is designed to pick up on regular human speech.

Talk like a normal person, and your voice assistant will respond best. Instead of “Alexa, alarm 7!” say, “Alexa, set an alarm for 7 in the morning.”

4. Create profiles for various family members

You can train Amazon’s Alexa to recognize up to six different people. This tip can be handy if you have family members with foreign accents or children at varying levels of language development. It’s an easy process and you can let Alexa slowly adjust to various voices.

Here’s how to set up Alexa profiles:

• Open the Alexa app.

• Tap More > Settings.

• Select Your Profile.

• Next to Voice, select Create.

• Select Continue.

You can also train Siri to recognize your voice. Take this extra step if you have an accent or speak quickly. You likely did this when you set up your phone, but try again if you and Siri aren’t getting along.

• Open Settings on your iPhone.

• Click on Siri & Search.

• Toggle the switch next to Listen for “Hey Siri” off and back on.

• Complete the on-screen setup process to train Siri to recognize your voice.

You can also teach Siri how to pronounce the names of people in your life, so you call the right person. If Siri says a name wrong, say, “You pronounced it wrong” to set the smart assistant straight.

Google Assistant has a similar feature called Voice Match. You can teach Google Assistant how to recognize your commands more accurately.

• Open the Google Home app.

• Tap your profile picture or initials.

• Head to Assistant settings > Voice Match.

• Click Add Devices.

• Follow the on-screen directions.

5. Make your smart assistant smarter

Often, Alexa, Google Assistant, or Siri will ask for clarification about something you said. This can be annoying, but answering will help train the AI to know you better.

When you respond to clarify what you were asking about in the first place, it shows your smart assistant how to do better in the future. Every clarification you make, your AI technology remembers and adapts to, making it less likely for you to have to repeat yourself next time.

There are, however, some questions and settings that might be worth the annoyance. Tap or click for fixes to 5 irritating Echo settings.

Check out my podcast “Kim Komando Explains” on Apple, Google Podcasts, or your favorite podcast player.

ProPublica obtained IRS information showing how billionaires like Bezos, Musk and Buffett pay little in income tax when compared to their massive wealth – sometimes, even nothing. I sat down with an experienced tax accountant who works with wealthy clients to get the scoop. Plus, we talked about special tax credits to lower your taxes.

Learn about all the latest technology on the Kim Komando Show, the nation’s largest weekend radio talk show. Kim takes calls and dispenses advice on today’s digital lifestyle, from smartphones and tablets to online privacy and data hacks. For her daily tips, free newsletters and more, visit her website at Komando.com.

The views and opinions expressed in this column are the author’s and do not necessarily reflect those of USA TODAY.

How to train siri cortana and google to understand your voice better

Recent technological developments in the area of speech recognition not only made our life more convenient and our workflow more productive, but also open opportunities, that were deemed as “miraculous” back in the days.

Speech-to-text software has a wide variety of applications, and the list continues to grow on a yearly basis. Healthcare, improved customer service, qualitative research, journalism – these are just some of the industries, where voice-to-text conversion has already become a major game-changer.

Why Do We Need Automatic Transcription?

Professionals in various areas need high-quality transcripts to perform their work-related activities. The technology behind the voice recognition advances at a fast pace, making it quicker, cheaper and more convenient than manual transcription.

Although the tech is not there yet to reach human performance, the software’s accuracy can get up to 95%. Transcription services used to be time-consuming and labor-intensive, whereas now human involvement in this process is limited to making small adjustments.

One More Reason – Digital accessibility

Why is Automatic Speech Recognition currently booming here in Europe? The answer is quite simple – digital accessibility. As described in the EU Directive 2016/2102, governments must take measures to ensure that everyone has equal access to information. Podcasts, videos and audio recordings need to be supplied with captions or transcripts to be accessible by people with hearing disabilities.

How Does Automatic Speech Recognition Work?

P.s – if that’s too much for you to read at the moment, feel free to skip to the summarizing infographic at the bottom of this page.

The core of an automatic transcription service is the automatic speech recognition system. In brief, such systems are composed by acoustic and linguistic components running on one or several computers.

The acoustic component is responsible of converting the audio in your file into a sequence of acoustic units – super small sound samples. Have you ever seen a waveform of the sound? That’s we call analogue sound or vibrations that you create when you speak – they are converted to digital signals, so that the software can analyze them. Then, mentioned acoustic units are matched to existing “phonemes” – those are the sounds that we use in our language to form meaningful expressions.

Thereafter, the linguistic component is responsible of converting these sequence of acoustic units into words, phrases, and paragraphs. There are many words that sound similar, but mean entirely different things, such as peace and piece.

The linguistic component analyzes all the preceding words and their relationship to estimate the probability which word should be used next. Geeks call these “Hidden Markov Models” – they are widely used in all speech recognition software. That’s how speech recognition engines are able to determine parts of speech and word endings (with varied success).

Example: he listens to a podcast. Even if the sound “s” in the word “listens” is barely pronounced, the linguistic component can still determine that the word should be spelled with “s”, because it was preceded by “he”.

You can easily test it in real life, as any other speech application, Google Translate has language models behind it. You can voice type a random word that has several meanings, and then supply the translator with a context (by putting a word in a sentence) – it is very likely that you’ll see more accurate transcription and translation.

Before you are able to use an automatic transcription service, these components must be trained appropriately to understand a specific language. Both, the acoustic part of your content, that is, how it is being spoken and recorded, and the linguistic part, that is, what is being said, are critical for the resulting accuracy of the transcription.

Here at Amberscript, we are constantly improving our acoustic and linguistic components in order to perfect our speech recognition engine.