Maswali ya Maneno ya Kuchunguza na Kuamsha Maneno

Majibu na maelezo huonekana unapojibu maswali.

1. Je, kazi ya msingi ya kigunduzi cha maneno ya kuamsha ni nini?
   • Ili kugundua wakati kishazi mahususi cha kianzishi kimezungumzwa
   • Ili kunakili kila neno ambalo mtumiaji anasema kwa maandishi
   • Ili kutafsiri hotuba katika lugha nyingine
   • Ili kubana sauti kwa hifadhi ya wingu
2. Kwa nini wazungumzaji wengi mahiri hutumia muundo wa ugunduzi wa hatua mbili?
   • Ili kusaidia lugha mbili tofauti mara moja
   • Kuruhusu chipu ya nishati ya chini ichunguze kabla ya muundo mkubwa kuthibitisha, kuokoa betri
   • Ili kurekodi nakala mbili za sauti kwa nakala rudufu
   • Kuendesha visaidizi viwili tofauti vya sauti kwa wakati mmoja
3. 'Kukubali kwa uwongo' kunamaanisha nini katika ugunduzi wa maneno-wake?
   • Kifaa hupuuza kifungu cha vichochezi kinachotamkwa kwa usahihi
   • Kifaa hukosea neno moja kama lingine katika sentensi
   • Kifaa huamka ingawa hakuna mtu aliyesema maneno ya kuchochea
   • Kifaa kinashindwa kuunganishwa kwenye mtandao
4. Takriban ni jinsi gani sauti inayoingia inatayarishwa kabla ya mtandao wa neva kuiona?
   • Inahifadhiwa kama faili ya MP3 ya urefu kamili kwanza
   • Inabadilishwa moja kwa moja kuwa sentensi zilizoandikwa
   • Inatumwa bila kubadilishwa kwa seva ya mbali kwa uchambuzi
   • Imekatwa katika fremu fupi zinazopishana na kugeuzwa kuwa vipengele vya akustisk kama vile MFCCs au mel energy.
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