引導式測驗 · 中等 等級
WaveNet 測驗
回顧 WaveNet 的自回歸波形產生、因果擴張卷積以及其原始取樣過程為何緩慢的原因。
問題 1 的 8
WaveNet 如何產生音訊?
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。
- WaveNet 如何產生音訊?
- 一次一個原始樣本,以之前的樣本為條件
- 透過從固定庫中選擇剪輯
- 透過將頻譜圖直接轉換為文本
- 所有樣品同時進行,無需訂購
- WaveNet 的關鍵卷積創新是什麼?
- 最大池化層數
- 擴張因果卷積
- 僅循環門
- 全連接層
- How did the original WaveNet represent quantized waveform samples for prediction?
- As a single continuous average for the entire clip
- As speaker IDs only
- As a categorical distribution over 256 µ-law-quantized values
- As a sequence of image patches
- 最初的 WaveNet 的主要實際缺點是什麼?
- 只能產生沉默
- 它不需要訓練數據
- 它只適用於圖像
- 順序採樣使得生成速度變慢
- In the speech-synthesis experiments described in the WaveNet paper, what does the model generate?
- Raw speech waveforms sample by sample, conditioned on linguistic features
- A mel-spectrogram that is itself the final audio
- Only phoneme labels without audio
- A MIDI score
- 哪個組織引進了 WaveNet?
- 美國太空總署
- DeepMind
- OpenAI
- Adobe
- What does causal convolution prevent in WaveNet?
- Using preceding samples as context
- Generating any audio waveform
- Using future audio samples to predict the current sample
- Conditioning on text or speaker features
- What activation structure does the original WaveNet use in its gated convolutional layers?
- A ReLU output concatenated with image patches
- A softmax over speakers only
- A linear layer without nonlinearities
- A tanh-filter output multiplied elementwise by a sigmoid gate