Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

X-Vector Agbọrọsọ ifibọ adanwo

Review x-vector identity features, TDNN temporal context, statistics pooling, hidden-layer embeddings, and scoring methods for speaker comparison.

Jẹmọ itọsọna awọn ọnaX Vector Agbọrọsọ ifibọ
Ibeere 1 ti 8

What information is a speaker-recognition x-vector designed to emphasize?

Awotẹlẹ gbogbo ibeere8 ibeere

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

  1. What information is a speaker-recognition x-vector designed to emphasize?
    • Only the exact words spoken as text
    • Only the recording's file format
    • A guaranteed identity proof unaffected by recording conditions
    • Speaker-related characteristics rather than a transcript of the utterance
  2. Layer wo ni o yi iwifun gigun-ayipada pada si fekito gigun-ipari kan ṣoṣo ni nẹtiwọọki x-fekito?
    • A convolutional image àlẹmọ
    • Layer ikojọpọ awọn iṣiro ti o ṣe iṣiro itumọ ati iyapa boṣewa kọja akoko
    • A dropout Layer
    • A ik softmax lo bi awọn ifibọ ara
  3. Iru nẹtiwọọki nkankikan wo ni a lo ni aṣa lati yọ awọn-fekito x jade?
    • A generative adversarial nẹtiwọki
    • A akojọpọ igi ipinnu
    • Nẹtiwọọki Neural Idaduro Akoko (TDNN)
    • Apadasẹhin laini itele
  4. Bawo ni a ṣe ṣe afiwe awọn onisọpọ x-meji lati pinnu boya wọn wa lati agbọrọsọ kanna?
    • Nipa ibajọra cosine tabi ẹhin PLDA kan
    • Nipa kika awọn ọrọ ti o baamu
    • Nipa ifiwera awọn iwọn faili
    • Nipa ṣiṣe ayẹwo oṣuwọn ayẹwo ohun
  5. Which established representation supplied comparison baselines in the 2018 x-vector speaker-recognition study?
    • A visual image-token embedding
    • A text-only word-count vector
    • i-fekito
    • An audio file-size histogram
  6. Iru faaji tuntun wo ni o ni ilọsiwaju lori x-fekito Ayebaye pẹlu akiyesi ikanni ati ikojọpọ awọn iṣiro akiyesi?
    • ResNet-50 fun awọn aworan
    • GPT-2
    • YOLO
    • ECAPA-TDNN
  7. Why is the classic x-vector extracted from a hidden segment-level layer rather than used as the final training-speaker softmax output?
    • The hidden representation can be compared as an embedding instead of being limited to probabilities for the training speaker labels
    • The hidden layer contains the recording's text transcript
    • Softmax probabilities are the only place where acoustic information exists
    • Hidden layers cannot process an unseen recording
  8. What does a time-delay layer contribute before statistics pooling in an x-vector extractor?
    • It stores only a single final filename
    • It combines information from neighboring acoustic frames, building temporal context
    • It assigns a new random speaker label to every frame
    • It removes all time information before any acoustic processing