Koko Spotting ati Wake Words Quiz

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

1. Kini iṣẹ akọkọ ti oluwari ọrọ ji?
   • Lati ṣawari nigbati gbolohun ọrọ okunfa kan ti sọ
   • Lati kọ gbogbo ọrọ olumulo sọ sinu ọrọ
   • Lati tumọ ọrọ si ede miiran
   • Lati compress ohun fun ibi ipamọ awọsanma
2. Kini idi ti ọpọlọpọ awọn agbọrọsọ ọlọgbọn lo apẹrẹ wiwa ipele meji?
   • Lati ṣe atilẹyin awọn ede oriṣiriṣi meji ni ẹẹkan
   • Lati jẹ ki ërún agbara kekere ṣe ayẹwo ti o ni inira ṣaaju ki awoṣe ti o tobi ju jẹrisi, fifipamọ batiri
   • Lati ṣe igbasilẹ awọn ẹda meji ti ohun naa fun afẹyinti
   • Lati ṣiṣẹ awọn oluranlọwọ ohun lọtọ meji ni nigbakannaa
3. Kini 'gbigba eke' tumọ si ni wiwa ọrọ-ji?
   • Ẹrọ naa kọju si ọrọ ti o nfa ọrọ ti o tọ
   • Ẹrọ naa padanu ọrọ kan bi omiiran ninu gbolohun ọrọ kan
   • Ẹrọ naa ji bi o tilẹ jẹ pe ko si ẹnikan ti o sọ gbolohun okunfa naa
   • Ẹrọ naa kuna lati sopọ si intanẹẹti
4. Ni aijọju bawo ni a ṣe pese ohun afetigbọ ti nwọle ṣaaju ki nẹtiwọọki nkankikan rii?
   • O ti wa ni ipamọ bi faili MP3 ipari ni akọkọ
   • O ti yipada taara si awọn gbolohun ọrọ kikọ
   • O ti firanṣẹ ko yipada si olupin latọna jijin fun itupalẹ
   • O ti ge wẹwẹ si awọn fireemu agbekọja kukuru o si yipada si awọn ẹya akositiki bii MFCC tabi awọn agbara 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