引導式測驗 · 中等 等級
X 向量揚聲器嵌入測驗
查看 x 向量身分特徵、TDNN 時間上下文、統計池、隱藏層嵌入和說話者比較的評分方法。
問題 1 的 8
What information is a speaker-recognition x-vector designed to emphasize?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 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
- 哪一層將可變長度話語轉換為 x 向量網路中的單一固定長度向量?
- 卷積影像濾波器
- 計算跨時間平均值和標準差的統計池層
- 一個dropout層
- 最終的 softmax 用作嵌入本身
- 傳統上使用什麼類型的神經網路來提取 x 向量?
- 生成對抗網絡
- 決策樹集成
- 時滯神經網路 (TDNN)
- 簡單的線性迴歸
- 通常如何比較兩個 x 向量來決定它們是否來自同一說話者?
- 透過餘弦相似度或 PLDA 後端
- 透過計算匹配單字
- 透過比較檔案大小
- 透過檢查音頻取樣率
- 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
- 哪種較新的架構透過通道注意力和注意力統計池改進了經典的 x 向量?
- 用於影像的 ResNet-50
- GPT-2
- 優洛
- ECAPA-TDNN
- 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
- 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