引导式测验 · 中等 等级

Jasper 和 QuartzNet ASR 测验

比较Jasper和QuartzNet的卷积设计和报告的配置，然后测试CTC解码和可分离滤波器的算法。

相关引导路径碧玉和石英石 Asr
问题 1 的 8

哪种分解方式区分 QuartzNet 的时空可分离卷积与稠密时间卷积？

预览每个问题8 问题

当您参加测验时，就会出现答案和解释。

  1. 哪种分解方式区分 QuartzNet 的时空可分离卷积与稠密时间卷积？
    • 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. 在 QuartzNet 论文中所述比较中，QuartzNet-15x5 与 JasperDR-10x5 在 3.33 亿参数时，列出的近似计数是多少？
    • 250 million
    • 5亿
    • 19 million
    • One billion
  3. 与引用的 Jasper 和 QuartzNet 研究论文相关的组织是哪一个？
    • Google
    • NVIDIA
    • Amazon
    • OpenAI
  4. Jasper 和 QuartzNet 使用什么损失函数在没有显式对齐的情况下进行训练？
    • 联结主义时间分类 (CTC)
    • 均方误差
    • 固定框架上的交叉熵
    • 三重态损失
  5. Jasper 卷积堆栈描述了哪种结构特征？
    • 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