Викторина, связанная с руководством · Средний Уровень
ASR-викторина Джаспера и QuartzNet
Сравните проекты свертки Jasper и QuartzNet и сообщенные конфигурации, затем протестируйте декодирование CTC и арифметику разделяемых фильтров.
Вопрос 1 из 8
Which factorization distinguishes QuartzNet’s time-channel separable convolution from a dense temporal convolution?
Предварительный просмотр каждого вопроса8 вопросы
Ответы и пояснения появляются по мере прохождения теста.
- Which factorization distinguishes QuartzNet’s time-channel separable convolution from a dense temporal convolution?
- Replacing every neural layer with a GMM
- Removing all channels from the input
- Adding a mandatory recurrent connection at every step
- Separate depthwise temporal filtering and pointwise channel mixing
- In the QuartzNet paper’s stated comparison, which approximate count is listed for QuartzNet-15x5 versus JasperDR-10x5 at 333 million parameters?
- 250 million
- 500 миллионов
- 19 million
- One billion
- Which organization is associated with the cited Jasper and QuartzNet research papers?
- NVIDIA
- Amazon
- OpenAI
- Какую функцию потерь используют Джаспер и QuartzNet для обучения без явного выравнивания?
- Коннекционистская временная классификация (CTC)
- Среднеквадратическая ошибка
- Перекрестная энтропия на фиксированных кадрах
- Тройная потеря
- Which structural feature is described for the Jasper convolutional stack?
- Only alphabetical sorting of frames
- A guarantee that all gradients have equal magnitude
- Residual connections
- Random deletion of every deep layer
- Which augmentation combination does the QuartzNet paper report for its best evaluated training setup?
- Only deleting all training transcriptions
- A required pronunciation dictionary replacement at each frame
- A guarantee that no data augmentation is used
- Speed perturbation with a cutout-style spectrogram method
- Under the stated CTC path mapping, what labels result from A, A, blank, A?
- AA
- A
- AAA
- An empty sequence
- For a length-three depthwise temporal filter on four input channels plus a pointwise map to eight output channels, how many filter weights are counted, excluding biases?
- 96
- 44
- 12
- 32