Ikibazo gihuza ibibazo · Hagati Urwego

MelGAN Ikibazo Cyibisambo Vocoder

Sobanukirwa uburyo amakarita ya MelGAN ashushanya mel-spectrogramu kugirango ahindurwe, akoreshe hejuru, kandi atoza ivangura kumunzani.

Inzira zijyanye no kuyoboraMelgan Vocoder
Ikibazo 1 Bya 8

Ni ubuhe butumwa MelGAN ihindura mu majwi mbisi?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Ni ubuhe butumwa MelGAN ihindura mu majwi mbisi?
    • Ikirangantego
    • Inyuguti nto
    • Idosiye ya MIDI
    • Umuyoboro wa foneme
  2. Kuki MelGAN yihuta cyane kuruta WaveNet?
    • Ikoresha igipimo gito cy'icyitegererezo
    • Ntabwo ari autoregressive kandi itanga amajwi murwego rumwe
    • Ikora kuri TPU gusa
    • Isimbuka imirongo myinshi yumurongo
  3. Ni ubuhe buryo bwihariye bwo kuvangura MelGAN yazanye?
    • Ivangura rimwe ku isi
    • Ivangura rishingiye ku ivangura
    • Ivangura rinini rikorera kumajwi kumyanzuro myinshi
    • Nta vangura na gato
  4. Niki gihombo gifasha guhagarika imyitozo yo guhangana na MelGAN?
    • Kwambukiranya-entropiya ku kimenyetso cyanditse
    • Gereranya gutakaza ibitekerezo
    • Igihombo cya gatatu
    • Igihombo-gihuza igihombo hagati yimikorere ivangura
  5. Nigute generator ya MelGAN yongera umurima wakira?
    • Ukoresheje imyanzuro yagutse mubice bisigaye
    • Wongeyeho inshuro nyinshi LSTM
    • Ukoresheje kwitondera hejuru ya clip yose
    • Mugutondekanya ibice
  6. What subjective evaluation measure did the MelGAN paper report?
    • Word error rate (WER)
    • Mean Opinion Score (MOS)
    • BLEU score
    • Peak signal-to-noise ratio (PSNR) only
  7. What do MelGAN’s transposed convolutions do in the generator?
    • Convert the waveform back into text
    • Choose the phonemes in the input sentence
    • Upsample the mel-spectrogram representation toward the audio waveform rate
    • Reduce the number of audio samples to zero
  8. Which audio domains did the MelGAN paper use to illustrate the generality of its techniques?
    • Machine translation, image captions, and video subtitling
    • Only speech recognition and speaker identification
    • Text summarization, code generation, and image classification
    • Speech synthesis, music-domain translation, and unconditional music synthesis