Тест, свързан с ръководство · Среден Ниво

Wav2Letter Convolutional ASR тест

Оценете акустичния дизайн на wav2letter и целта на ASG, с разликите между оригиналните експерименти, по-късните инструменти на C++ и рецептивните полета.

Свързани ръководни пътекиWav2letter Convolutional Asr
Въпрос 1 на 8

Which architecture defines the original wav2letter acoustic network?

Визуализирайте всеки въпрос8 въпроси

Отговорите и обясненията се появяват, докато отговаряте на теста.

  1. 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
  2. Which research organization is associated with the original 2016 wav2letter paper?
    • Google Мозък
    • Microsoft Изследване
    • Facebook AI Research
    • NVIDIA
  3. 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
  4. Как се различава първоначалната загуба на AutoSegCriterion (ASG) от по-често срещаната загуба на CTC?
    • Той премахва празния символ и директно моделира преходите на буквите
    • Изисква ръчно подравняване за всеки кадър
    • Работи само с RNN
    • Не може да обработва последователности с променлива дължина
  5. 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
  6. 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
    • Фенерче
  7. 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
  8. 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?
    • три
    • Пет
    • Шест
    • Девет