引導式測驗 · 中等 等級

聲音事件偵測測驗

研究聲音類別和時間邊界,包括複調、弱標籤、DCASE 基線、起始容差和缺失類別註釋。

相關引導路徑聲音事件偵測
問題 1 的 8

除了片段層級的標籤外,時間聲音事件偵測還估計了哪些額外的輸出?

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。

  1. 除了片段層級的標籤外,時間聲音事件偵測還估計了哪些額外的輸出?
    • Only the audio file’s compression ratio
    • Only its filename’s alphabetical order
    • Event onset and offset boundaries within the clip
    • Only the display color of a waveform
  2. 為什麼聲音事件檢測經常被描述為複調問題?
    • 因為它只處理音符
    • 因為多個聲音可以重疊同時出現
    • 因為它需要多個麥克風
    • 因為音訊始終是立體聲
  3. SED 訓練資料中的「弱標籤」是什麼意思?
    • 標籤已加密
    • 音頻品質很差
    • 僅標記安靜的聲音
    • 剪輯被標記為事件發生,但不準確是在何時發生
  4. 在引用的 DCASE 2024 基準中指出了哪種分類器結構?
    • A convolutional recurrent neural network with added pretrained frame features
    • Only a static spreadsheet sort
    • Only an unchanged relational database table
    • Only a mandatory image-file compressor
  5. 此處描述的記錄聲音偵測基準情境中使用了哪種時頻表示法?
    • Only a speech transcript
    • A log-mel representation
    • Only a JPEG photograph
    • Only an unchanged output filename
  6. Which cited research challenge supplies the 2018 and 2024 sound-event task settings discussed here?
    • 奧運
    • A retail shopping holiday
    • A mandatory social-network ranking
    • DCASE
  7. Considering only the DCASE 2018 onset collar of 200 ms, does a 1.15 s prediction satisfy it for a 1.00 s reference onset?
    • Yes; the onset error is 150 ms
    • No; the error is 1.15 s
    • No; every predicted onset must be numerically identical
    • Yes; onset errors are never evaluated
  8. In the heterogeneous 2024 task, how does the baseline handle outputs for classes whose annotations are missing in a training dataset?
    • Treats every unannotated class as certainly absent
    • Copies all missing labels from the final test answers
    • Masks those unavailable outputs in the relevant loss computation
    • Eliminates every labeled class from the model