EasyDeepLearn

Self-supervised audio — wav2vec 2 and HuBERT.

hard

Answer

  • Wav2Vec 2 (Facebook 2020): quantize audio features → mask spans → predict quantized targets via contrastive loss.
  • HuBERT: similar but uses clustered representations as pseudo-labels (BERT-style masked prediction).
  • Both dominated pretraining for ASR — supervised fine-tuning with ~10 hours of labeled speech reaches WER competitive with 1000+ hours of pure supervised training.
  • Foundation of Whisper's competitors and many production speech systems.
Check yourself — multiple choice
  • Random
  • Wav2Vec 2: contrastive on masked quantized audio; HuBERT: BERT-style masked prediction of clustered targets; foundation of low-supervision ASR
  • Same as CLIP
  • Not real

Audio SSL: Wav2Vec 2 (contrastive) / HuBERT (masked-cluster prediction).

#representation-learning#applications

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions