Barashada Kelmad-furaha iyo Kediska Kelmado Wake

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay shaqada aasaasiga ah ee baraaruga-ereyga?
   • Si loo ogaado marka odhaah gaar ah lagu hadlay
   • Si loo qoro erey kasta isticmaaluhu wuxuu dhahaa qoraal
   • Si hadalka loogu turjumo luqad kale
   • Si loo cadaadiyo maqalka kaydinta daruuraha
2. Maxay dad badan oo ku hadla caqli badan u adeegsadaan naqshad ogaansho laba heer ah?
   • Si loo taageero laba luuqadood oo kala duwan hal mar
   • Si aad u ogolaato in chip-ka tamarta yar uu sameeyo jeeg adag ka hor inta aanu model weyn xaqiijin, badbaadinta batteriga
   • Si loo duubo laba koobi oo maqalka ah si gurmad loo helo
   • Si aad isku mar u wada wadato laba kaaliye cod oo kala duwan
3. Waa maxay macnaha 'aqbalaad been ah' marka loo eego ogaanshaha kelmad toosan?
   • Qalabku waxa uu iska indhatiraa weedha kicinta ee sida saxda ah loogu hadlay
   • Qalabku wuxuu si khaldan u jeexjeexayaa hal erey oo kale jumlad ahaan
   • Qalabku wuu toosay inkasta oo qofna aanu odhan weedha kiciya
   • Qalabku wuu ku guul daraystay inuu ku xidhmo internetka
4. Qiyaas ahaan sidee loo diyaariyaa codka soo socda ka hor inta aan shabakada neerfaha arkin?
   • Waxa marka hore loo kaydiyay sidii faylka MP3 dhererkiisu dhan yahay
   • Waxa si toos ah loogu beddelaa weedho qoran
   • Waxa loo diraa iyada oo aan waxba laga beddelin serfer fog si loo baaro
   • Waxa loo qaybiyaa fiimyo gaagaaban oo is-dul-saaran oo loo beddelaa sifooyin dhawaaq sida MMFC-yada ama tamarta mel
5. What trade-off can raising a wake-word detector’s activation threshold create?
   • Fewer false accepts but potentially more false rejects or delayed detections
   • More false accepts and guaranteed zero false rejects
   • No change in either error rate under any audio condition
   • A guarantee that every user’s phrase is recognized
6. What result did Hello Edge report for its depthwise separable CNN on the Google Speech Commands evaluation?
   • 100% accuracy on all languages and devices
   • 95.4% accuracy, about 10% higher than a DNN with a similar parameter count
   • 95.4% lower memory use than every competing model
   • A 10% guaranteed battery-life increase for every microcontroller
7. What does a false reject mean in wake-word detection?
   • The detector activates without the wake word
   • The microphone records silence correctly
   • The user says the wake word but the detector does not activate
   • A speaker is assigned the wrong identity
8. Why may a wake-word system use a compact model on-device?
   • It guarantees zero false accepts
   • It replaces all speech recognition
   • It makes the wake phrase unnecessary
   • It can reduce dependence on network access and support low-power always-on detection