Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Tacotron 2

Kagua bomba la kuanzia maandishi hadi melini la Tacotron 2, ulinzi wa tahadhari, na ubashiri wa kusimamishwa ambao huamua urefu wa matamshi.

Njia za mwongozo zinazohusianaTakotini 2
Swali 1 ya 8

Tacotron 2 inatabiri uwakilishi gani wa kati kutoka kwa maandishi?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Tacotron 2 inatabiri uwakilishi gani wa kati kutoka kwa maandishi?
    • Mel-spectrogram
    • Picha ya JPEG
    • Fonimu za maandishi ghafi pekee
    • Faili ya MIDI
  2. Ni nini kinachobadilisha spectrogram ya Tacotron 2 kuwa muundo halisi wa wimbi?
    • Kikagua tahajia
    • Vokoda iliyorekebishwa ya WaveNet
    • Injini ya utafutaji
    • Kiainishi cha taswira cha kubadilisha
  3. Je, umakini unaozingatia eneo husaidia kuzuia tatizo gani?
    • Kuongeza joto kwa GPU
    • Kupoteza muunganisho wa intaneti
    • Maneno yanayorudiwa au kuruka wakati wa usanisi
    • Makosa ya tahajia katika maandishi ya ingizo
  4. How does Tacotron 2 determine that it has generated the end of an utterance?
    • A human must press a button for every utterance
    • It always generates a fixed number of frames
    • The vocoder detects silence and interrupts the decoder
    • A learned stop-token prediction signals the decoder to stop
  5. Ni mtindo gani wa usanifu wa jumla ambao sehemu ya maandishi-hadi-spectrogram hutumia?
    • Mfuatano-kwa-mfuatano kwa umakini
    • Jedwali rahisi la kuangalia
    • Mti wa maamuzi
    • Seti ya sheria tuli
  6. Ni mtindo gani wa baadaye ambao ni mrithi wa haraka, asiye na ubinafsi wa roho kwa Tacotron 2?
    • ResNet
    • FastSpeech 2
    • BERT
    • AlexNet
  7. What does the post-net in Tacotron 2 refine?
    • The input text spelling
    • The speaker’s identity metadata
    • The predicted mel-spectrogram
    • The final transcript punctuation
  8. What does FastSpeech 2 add as conditioning information for speech variation?
    • A video soundtrack transcript only
    • A random microphone serial number
    • A mandatory image embedding
    • Pitch, energy, and more accurate duration information