引導式測驗 · 中等 等級
用於語音辨識測驗的 SpecAugment
查看特徵域 SpecAugment、時間扭曲、頻率和時間遮罩及其特定的 LibriSpeech 和 Switchboard 結果。
問題 1 的 8
SpecAugment 的作用是什麼?
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。
- SpecAugment 的作用是什麼?
- 對數梅爾譜圖
- 原始音訊波形
- 文字記錄
- 模型的權重
- SpecAugment 的三個操作中哪一個是其中之一?
- 音高反轉
- 頻率掩蔽
- 單字替換
- 迴聲注射
- What role did the SpecAugment paper assign to its feature transformations?
- They guarantee that every recognizer avoids overfitting
- They replace the need for transcribed training data
- They augment ASR training inputs and were evaluated for recognition performance
- They improve every speech model by the same amount
- 「時間掩蔽」有什麼作用?
- 刪除轉錄時間戳
- 加快音訊播放速度
- 消除開始時的沉默
- 清空一段連續的時間步長
- How are time- and frequency-mask locations chosen during SpecAugment training?
- They are randomly sampled, so the same input may receive different masked regions on later passes
- They are fixed permanently before the training set is collected
- They are chosen by a language model after each recognition result
- They are identical for every utterance and every training step
- SpecAugment 在哪個基準上顯著幫助實現了最先進的結果?
- 影像網
- 圖書館演講
- 小隊
- 膠水
- What does time warping do in the original SpecAugment policy?
- It replaces speech frames with translated text
- It masks every frequency channel permanently
- It deforms feature positions along the time axis
- It changes the speaker identity in the waveform
- Which recognizer architecture did the original SpecAugment paper use in its experiments?
- A region-based image detector
- A music source-separation U-Net only
- A text-only masked language model
- Listen, Attend and Spell (LAS)