引导式测验 · 中等 等级
Wav2Letter 卷积 ASR 测验
评估 wav2letter 的声学设计和 ASG 目标，以及原始实验、后来的 C++ 工具和感受野之间的差异。
问题 1 的 8
Which architecture defines the original wav2letter acoustic network?
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。
- Which architecture defines the original wav2letter acoustic network?
- A recurrent-only network
- A decision-tree ensemble
- A Gaussian-mixture-only acoustic network
- A convolutional network without recurrent acoustic connections
- Which research organization is associated with the original 2016 wav2letter paper?
- Google 大脑
- Microsoft 研究
- Facebook AI Research
- NVIDIA
- Which output representation does the original wav2letter acoustic model predict from its studied speech inputs?
- Only an intermediate human-labeled phoneme transcript
- Letters or graphemes
- Only a list of speaker names
- Only a global tempo value
- 原始 AutoSegCriterion (ASG) 损失与更常见的 CTC 损失有何不同？
- 它删除了空白符号并直接模拟字母转换
- 它需要每帧手动对齐
- 它仅适用于 RNN
- 它无法处理可变长度序列
- What computation difference does a convolutional acoustic stack offer compared with a conventional recurrent dependency across time?
- Every complete speech decoder becomes fully parallel
- No labeled transcription data is needed for its supervised objective
- Convolution operations can be evaluated across positions without that recurrent chain
- Every workload necessarily obtains zero transcription error
- Which C++ machine-learning library documents ASR applications formerly associated with the wav2letter project?
- scikit-learn only
- An audio-compression format
- A required spelling dictionary standard
- 手电筒
- Which tensor library does the later wav2letter++ paper identify for its C++ framework?
- ArrayFire
- A required Java virtual machine
- Only the original Torch7 runtime
- A fixed spreadsheet engine
- For two length-three temporal convolutions at stride one and dilation one with no padding or intervening operation, how many original positions can one second-layer output depend on?
- 三
- 五
- 六
- 九