Ikibazo gihuza ibibazo · Hagati Urwego

Umva Kwitabira no Kwandika Ikibazo

Ongera usuzume LAS abumva-imyandikire, kugabanya igihe cya piramide, kwitondera, ibisubizo byimiterere, hamwe nisuzuma ryumwimerere.

Inzira zijyanye no kuyoboraUmva Kwitabira no Kwandika
Ikibazo 1 Bya 8

Nibihe bintu bibiri byingenzi bigize moderi ya LAS?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Nibihe bintu bibiri byingenzi bigize moderi ya LAS?
    • Umva na Speller
    • Encoder na tokenizer
    • Imashini itanga ivangura
    • Akayunguruzo
  2. Niki Speller muri LAS isohoka?
    • Fonemes yo mu nkoranyamagambo
    • Inyuguti, imwe imwe
    • Amagambo yose gusa
    • Ikirangantego
  3. Kuki kodegisi ya LAS yitwa 'piramide'?
    • Ifite nka mpandeshatu kuri ecran
    • Ikoresha GPU eshatu
    • Igabanya igihe cyo gukemura kuri buri cyiciro
    • I piramide igihombo cyagaciro
  4. Nibihe bintu bishaje LAS idasanzwe idasaba?
    • Mikoro
    • Igikorwa cyo gutakaza
    • Amahugurwa
    • Inkoranyamagambo yubatswe n'intoki
  5. Ni ubuhe buryo butuma Speller yibanda ku gice kijyanye n'amajwi kuri buri nyuguti?
    • Icyitonderwa
    • Kureka
    • Ibisanzwe
    • Gutema ibiti
  6. Ni ubuhe buryo bumwe bugarukira bwa mbere bwa LAS?
    • Ntishobora gukora ku byuma ibyo aribyo byose
    • Ntiyari itemba, ikeneye imvugo yuzuye mbere yo gushushanya
    • Isohora gusa imibare
    • Byasabye inkoranyamagambo
  7. What WER did the LAS paper report on its Google voice-search subset without a language model?
    • 1.41%
    • 41.0%
    • 14.1%
    • 80.0%
  8. What distinction does the LAS paper make about dependencies among output characters?
    • It predicts each character independently with no sequence model
    • It outputs only phoneme classes and forbids character context
    • It requires a separate dictionary to define character dependencies
    • The model emits character sequences without assuming the characters are independent