Ikibazo gihuza ibibazo · Hagati Urwego

Ijambo ryibanze Gutondeka no Gukangura Amagambo Ikibazo

Ongera usubiremo ijambo ryibanze, gutahura, kwemeza ibinyoma, ibiranga amajwi, ibyiringiro byigihe gito, hamwe nimbogamizi kubikoresho.

Ikibazo 1 Bya 8

Nuwuhe murimo wibanze wumukangurambaga-ijambo?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Nuwuhe murimo wibanze wumukangurambaga-ijambo?
    • Kumenya igihe interuro yihariye yatanzwe
    • Kwandukura ijambo ryose umukoresha avuga mumyandiko
    • Guhindura imvugo mu rundi rurimi
    • Guhagarika amajwi yo kubika ibicu
  2. Kuki abavuga rikijyana benshi bakoresha igishushanyo mbonera?
    • Gushyigikira indimi ebyiri zitandukanye icyarimwe
    • Kureka imbaraga nkeya chip gukora igenzura mbere yuko moderi nini yemeza, ikiza bateri
    • Kwandika kopi ebyiri zamajwi kugirango zisubizwe
    • Gukoresha amajwi abiri atandukanye abafasha icyarimwe
  3. Bisobanura iki 'kubeshya kubeshya' bisobanura gukanguka-ijambo gutahura?
    • Igikoresho cyirengagije imvugo ikurura neza
    • Igikoresho cyumva nabi ijambo rimwe nkiryo mu nteruro
    • Igikoresho kirabyuka nubwo ntamuntu numwe wavuze interuro
    • Igikoresho cyananiwe guhuza na enterineti
  4. Hafi yukuntu amajwi yinjira ategurwa mbere yuko umuyoboro wimitsi ubibona?
    • Yabitswe nka dosiye yuzuye ya MP3 mbere
    • Ihindurwa mu nteruro yanditse
    • Yoherejwe idahindutse kuri seriveri ya kure kugirango isesengurwe
    • Yaciwemo ibice bigufi byuzuye kandi bihinduka ibintu bya acoustic nka MFCCs cyangwa ingufu za mel
  5. Ni ubuhe bucuruzi bushobora kuzamura ibyuka-ijambo detektori yo gukora?
    • 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