SpecAugment fun Ọrọ Idanwo Idanwo

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

1. Kini SpecAugment nṣiṣẹ lori?
   • Awọn log-mel spectrogram
   • Awọn aise iwe igbi
   • Tiransikiripiti ọrọ
   • Awọn iwọn awoṣe
2. Ewo ninu iwọnyi jẹ ọkan ninu awọn iṣẹ mẹta ti SpecAugment?
   • Iyipada ipolowo
   • Igbohunsafẹfẹ boju
   • Iyipada ọrọ
   • Abẹrẹ iwoyi
3. 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
4. Kí ni 'akoko masking' ṣe?
   • Npa awọn aami igba iwe kikowe rẹ kuro
   • Mu ṣiṣe ṣiṣiṣẹsẹhin ohun soke
   • Yọ ipalọlọ ni ibẹrẹ
   • Òfo jade a igba ti itẹlera akoko awọn igbesẹ
5. 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
6. Lori ala wo wo ni SpecAugment ṣe iranlọwọ ni pataki lati ṣaṣeyọri awọn abajade-ti-ti-aworan?
   • Pipa Net
   • LibriSpeech
   • SQuAD
   • GÚN
7. 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
8. 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)