quiz bu lëkkale ak tegtal · Diggante Niveau
Laaj ak tontu ci audio
Xoolaat leeral audio yi ak transkripsioŋ kàddu yi, ak Clotho ak AudioCaps, encoder-decoder, jàngat CIDEr, ak royuwaayi Clotho yu njëkk ya.
Laaj 1 de 8
Lan moo wuutale sous-titre audio ak xàmmee kàddu yi ci saa si?
Xoolaatal laaj bu nekk8 laaj
Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.
- Lan moo wuutale sous-titre audio ak xàmmee kàddu yi ci saa si?
- Du dox ludul ci noppi
- Dafa gëna yeex waaye dafay nuru ci génne
- Dafay fësal seen akustik bi yépp, du bind kàddu yuñ wax
- Dafay soppi mbind mu nekk audio
- Which published datasets supply general-audio descriptions for captioning in this guide?
- MNIST and CIFAR only
- Clotho ak AudioCaps
- A mandatory bank-transaction table
- Only a raw network-password list
- What architecture does the cited original Clotho baseline use to produce caption words from audio features?
- Only a fixed filename lookup
- Only a volume meter with no text output
- Only an unchanged grammar rule list
- An encoder-decoder scheme with attention
- Lan moo waral sous-titre audio am solo ngir yombal jëfandikoo gi?
- Dafay leeral son yi mënul wax ngir tëx yi ak ñiy dégg bu baax
- Dafay yokk volume audio bi
- Dafay efaase bruit yi ci ginaaw
- Dafay enkripte audio bi
- Which reference-comparison metric does the Clotho paper use among its caption evaluations?
- RGB color values
- Cider
- Audio sample rate alone
- Only a decibel reading
- Lan mooy jafe-jafe bi gëna mag bi am ci wàllu sous-titre audio?
- Fichier audio yi dañu tuuti lool ngir ñu mëna jëfandikoo
- Amul ay done yuñ mëna am
- Benn baat kese lañu mëna am ci guddaay
- Defar ay tegtal yu dëggu te moytu ay detay yu baaxul
- How many reference captions per audio file does the original Clotho paper report?
- Juroom
- Benn
- Fifteen
- Téeméer
- How many log-mel-band features form each input frame in the original Clotho baseline described in the paper?
- 8
- 20
- 64
- 256