WaveNet Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. WaveNet inoburitsa sei odhiyo?
   • Imwe sampuli yakasvibirira panguva, yakarongedzwa pamasampuli apfuura
   • Nekusarudza zvimedu kubva muraibhurari yakatarwa
   • Nekushandura spectrograms zvakananga kune zvinyorwa
   • Masampuli ese panguva imwe chete pasina kurongeka
2. Chii chakakosha convolutional innovation muWaveNet?
   • Max pooling layers
   • Dilated causal convolutions
   • Recurrent magedhi chete
   • Zvizere zvakabatanidzwa zvikamu
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. Chii chaive chikuru chinoshanda chekudzosera kumashure kweiyo WaveNet yekutanga?
   • Chaigona kungoburitsa runyararo
   • Zvaisada data rekudzidziswa
   • Yakashanda pamifananidzo chete
   • Sequential sampling yakaita chizvarwa chinonoke
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. Nderipi sangano rakaunza 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