quiz bu lëkkale ak tegtal · Diggante Niveau
Tacotron 2 quiz
Xoolaat Tacotron 2's text-to-mel pipeline, bàyyi xel ci kaaraange, ak jàngat stop prediction biy wane guddaayi wax.
Laaj 1 de 8
Lan mooy diggante bi Tacotron 2 di wax ci mbind mi?
Xoolaatal laaj bu nekk8 laaj
Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.
- Lan mooy diggante bi Tacotron 2 di wax ci mbind mi?
- Spektrogram mel
- Nataalu JPEG
- Fonem yu ñor kese
- Dosie MIDI
- Lan mooy soppi spectrogram bu Tacotron 2 ci forme onde bu dëggu?
- Saytu ortograafi
- Vokoder WaveNet buñ soppali
- Motëru seetlu
- ab xaajkat nataal buy boole
- Ban jafe-jafe la bàyyi xel ci barab bi di jàppale ngir moytu?
- GPU bi di tàng lool
- Koneksioŋ internet bi daa ñàkk
- Baatu-baatu yuñ baamtu wala yuñ sànni ci diiru synthese
- Jumtukaayi ortograafi ci mbind yiñ dugal
- 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
- Ban stil architecture la wàllu text-ci-spectrogram bi di jëfandikoo?
- toppalante ak toppalante ak bàyyi xel
- Tablo seetlu bu yomb
- Garab buy jël dogal
- Regle bu fippu
- Ban model ci ginaaw moo gëna gaaw, te du dellu ginaaw ci ngëm ci Tacotron 2?
- Resnet
- Kaddu yu Gaaw 2
- Bert
- AlexNet
- 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
- 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