引导式测验 · 中等 等级

X 向量扬声器嵌入测验

查看 x 向量身份特征、TDNN 时间上下文、统计池、隐藏层嵌入和说话者比较的评分方法。

相关引导路径X 矢量扬声器嵌入
问题 1 的 8

What information is a speaker-recognition x-vector designed to emphasize?

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. What information is a speaker-recognition x-vector designed to emphasize?
    • Only the exact words spoken as text
    • Only the recording's file format
    • A guaranteed identity proof unaffected by recording conditions
    • Speaker-related characteristics rather than a transcript of the utterance
  2. 哪一层将可变长度话语转换为 x 向量网络中的单个固定长度向量？
    • 卷积图像滤波器
    • 计算跨时间平均值和标准差的统计池层
    • 一个dropout层
    • 最终的 softmax 用作嵌入本身
  3. 传统上使用什么类型的神经网络来提取 x 向量？
    • 生成对抗网络
    • 决策树集成
    • 时滞神经网络 (TDNN)
    • 简单的线性回归
  4. 通常如何比较两个 x 向量来确定它们是否来自同一说话人？
    • 通过余弦相似度或 PLDA 后端
    • 通过计算匹配单词
    • 通过比较文件大小
    • 通过检查音频采样率
  5. Which established representation supplied comparison baselines in the 2018 x-vector speaker-recognition study?
    • A visual image-token embedding
    • A text-only word-count vector
    • i-向量
    • An audio file-size histogram
  6. 哪种较新的架构通过通道注意力和注意力统计池改进了经典的 x 向量？
    • 用于图像的 ResNet-50
    • GPT-2
    • 优洛
    • ECAPA-TDNN
  7. Why is the classic x-vector extracted from a hidden segment-level layer rather than used as the final training-speaker softmax output?
    • The hidden representation can be compared as an embedding instead of being limited to probabilities for the training speaker labels
    • The hidden layer contains the recording's text transcript
    • Softmax probabilities are the only place where acoustic information exists
    • Hidden layers cannot process an unseen recording
  8. What does a time-delay layer contribute before statistics pooling in an x-vector extractor?
    • It stores only a single final filename
    • It combines information from neighboring acoustic frames, building temporal context
    • It assigns a new random speaker label to every frame
    • It removes all time information before any acoustic processing