Kvíz spojený s průvodcem · Střední úroveň

Jasper a QuartzNet ASR kvíz

Porovnejte konvoluční návrhy Jasper a QuartzNet a nahlášené konfigurace a poté otestujte dekódování CTC a aritmetiku oddělitelných filtrů.

Související vodicí cestyJasper A Quartznet Asr
Otázka 1 z 8

Which factorization distinguishes QuartzNet’s time-channel separable convolution from a dense temporal convolution?

Náhled každé otázky8 otázky

Odpovědi a vysvětlení se zobrazují, jak budete v kvízu.

  1. Which factorization distinguishes QuartzNet’s time-channel separable convolution from a dense temporal convolution?
    • Replacing every neural layer with a GMM
    • Removing all channels from the input
    • Adding a mandatory recurrent connection at every step
    • Separate depthwise temporal filtering and pointwise channel mixing
  2. In the QuartzNet paper’s stated comparison, which approximate count is listed for QuartzNet-15x5 versus JasperDR-10x5 at 333 million parameters?
    • 250 million
    • 500 milionů
    • 19 million
    • One billion
  3. Which organization is associated with the cited Jasper and QuartzNet research papers?
    • Google
    • NVIDIA
    • Amazon
    • OpenAI
  4. Jakou ztrátovou funkci používají Jasper a QuartzNet k trénování bez explicitního zarovnání?
    • Connectionist Temporal Classification (CTC)
    • Střední kvadratická chyba
    • Křížová entropie na pevných rámcích
    • Trojnásobná ztráta
  5. Which structural feature is described for the Jasper convolutional stack?
    • Only alphabetical sorting of frames
    • A guarantee that all gradients have equal magnitude
    • Residual connections
    • Random deletion of every deep layer
  6. Which augmentation combination does the QuartzNet paper report for its best evaluated training setup?
    • Only deleting all training transcriptions
    • A required pronunciation dictionary replacement at each frame
    • A guarantee that no data augmentation is used
    • Speed perturbation with a cutout-style spectrogram method
  7. Under the stated CTC path mapping, what labels result from A, A, blank, A?
    • AA
    • A
    • AAA
    • An empty sequence
  8. For a length-three depthwise temporal filter on four input channels plus a pointwise map to eight output channels, how many filter weights are counted, excluding biases?
    • 96
    • 44
    • 12
    • 32