Ikibazo gihuza ibibazo · Hagati Urwego

Kwiyongera kubibazo byo kumenya imvugo

Ongera usuzume ibiranga-indangarubuga Yongeyeho, igihe, inshuro hamwe na masike yigihe, hamwe nibisubizo byihariye bya LibriSpeech na Switchboard.

Inzira zijyanye no kuyoboraKwiyongera Kumenyekanisha Imvugo
Ikibazo 1 Bya 8

Niki SpecAugment ikora?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niki SpecAugment ikora?
    • Ikirangantego
    • Amajwi mbisi
    • Inyandiko mvugo
    • Ibipimo by'icyitegererezo
  2. Niki muribi murimwe mubikorwa bitatu bya SpecAugment?
    • Gusubira inyuma
    • Guhisha inshuro
    • Gusimbuza ijambo
    • Gutera urusaku
  3. What role did the SpecAugment paper assign to its feature transformations?
    • They guarantee that every recognizer avoids overfitting
    • They replace the need for transcribed training data
    • They augment ASR training inputs and were evaluated for recognition performance
    • They improve every speech model by the same amount
  4. 'Guhisha umwanya' gukora iki?
    • Gusiba inyandiko-mvugo yerekana igihe
    • Kwihutisha gukina amajwi
    • Kuraho guceceka mugitangira
    • Kuraho umwanya wintambwe ikurikiranye
  5. How are time- and frequency-mask locations chosen during SpecAugment training?
    • They are randomly sampled, so the same input may receive different masked regions on later passes
    • They are fixed permanently before the training set is collected
    • They are chosen by a language model after each recognition result
    • They are identical for every utterance and every training step
  6. Ni ibihe bipimo SpecAugment yafashije cyane kugera ku bisubizo bigezweho?
    • IshushoNet
    • Ubuntu
    • SQuAD
    • GLUE
  7. What does time warping do in the original SpecAugment policy?
    • It replaces speech frames with translated text
    • It masks every frequency channel permanently
    • It deforms feature positions along the time axis
    • It changes the speaker identity in the waveform
  8. Which recognizer architecture did the original SpecAugment paper use in its experiments?
    • A region-based image detector
    • A music source-separation U-Net only
    • A text-only masked language model
    • Listen, Attend and Spell (LAS)