Laajte WaveNet

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. naka la WaveNet di defaree audio?
   • Benn misaal bu ñor benn yoon, buñu sukkandikoo ci misaal yi njëkk
   • Soo tànnee ay clip ci bibliotek bu fiks
   • Ni ñuy soppi spectrogram yi ci mbind
   • misaal yépp benn yoon te kenn du komànde
2. Lan mooy jéego yu am solo yi ci WaveNet?
   • Max couches pooling
   • Konvolusioŋ sabab yu yaatu
   • Buntu yuy baaxoo rek
   • Layers yu boole lépp
3. How did the original WaveNet represent quantized waveform samples for prediction?
   • As a single continuous average for the entire clip
   • As speaker IDs only
   • As a categorical distribution over 256 µ-law-quantized values
   • As a sequence of image patches
4. Lan moo nekkoon njariñ li gëna mag ci WaveNet bi njëkk?
   • Mënul jur ludul noppalu
   • Soxlawolen ay done tàggat
   • Ci nataal rek lay dox
   • Sampling yu toppalante taxna defar bi yeex
5. In the speech-synthesis experiments described in the WaveNet paper, what does the model generate?
   • Raw speech waveforms sample by sample, conditioned on linguistic features
   • A mel-spectrogram that is itself the final audio
   • Only phoneme labels without audio
   • A MIDI score
6. Ban mbootaay moo dugal WaveNet?
   • NASA
   • DeepMind
   • OpenAI
   • Adobe
7. What does causal convolution prevent in WaveNet?
   • Using preceding samples as context
   • Generating any audio waveform
   • Using future audio samples to predict the current sample
   • Conditioning on text or speaker features
8. What activation structure does the original WaveNet use in its gated convolutional layers?
   • A ReLU output concatenated with image patches
   • A softmax over speakers only
   • A linear layer without nonlinearities
   • A tanh-filter output multiplied elementwise by a sigmoid gate