Quiz collegato alla guida · Medio Livello
Quiz ASR convoluzionale Wav2Letter
Valuta la progettazione acustica di wav2letter e l'obiettivo ASG, con le differenze tra gli esperimenti originali, gli strumenti C++ successivi e i campi recettivi.
Domanda 1 di 8
Which architecture defines the original wav2letter acoustic network?
Anteprima di ogni domanda8 domande
Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.
- Which architecture defines the original wav2letter acoustic network?
- A recurrent-only network
- A decision-tree ensemble
- A Gaussian-mixture-only acoustic network
- A convolutional network without recurrent acoustic connections
- Which research organization is associated with the original 2016 wav2letter paper?
- Google Cervello
- Microsoft Ricerca
- Facebook AI Research
- NVIDIA
- Which output representation does the original wav2letter acoustic model predict from its studied speech inputs?
- Only an intermediate human-labeled phoneme transcript
- Letters or graphemes
- Only a list of speaker names
- Only a global tempo value
- In che modo la perdita AutoSegCriterion (ASG) originale differisce dalla più comune perdita CTC?
- Rimuove il simbolo vuoto e modella direttamente le transizioni delle lettere
- Richiede l'allineamento manuale per fotogramma
- Funziona solo con gli RNN
- Non può gestire sequenze di lunghezza variabile
- What computation difference does a convolutional acoustic stack offer compared with a conventional recurrent dependency across time?
- Every complete speech decoder becomes fully parallel
- No labeled transcription data is needed for its supervised objective
- Convolution operations can be evaluated across positions without that recurrent chain
- Every workload necessarily obtains zero transcription error
- Which C++ machine-learning library documents ASR applications formerly associated with the wav2letter project?
- scikit-learn only
- An audio-compression format
- A required spelling dictionary standard
- Torcia elettrica
- Which tensor library does the later wav2letter++ paper identify for its C++ framework?
- ArrayFire
- A required Java virtual machine
- Only the original Torch7 runtime
- A fixed spreadsheet engine
- For two length-three temporal convolutions at stride one and dilation one with no padding or intervening operation, how many original positions can one second-layer output depend on?
- Tre
- Cinque
- Sei
- Nove