Self-supervised audio — wav2vec 2 and HuBERT.
hardAnswer
- 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
- Node2Vec — how does it learn graph node embeddings?
- Self-supervised graph learning — approaches.
- How are multimodal embeddings unified across text / image / audio?
- Fine-tuning vs linear probe vs prompt-tuning — when do you use each?
- What is a 'foundation model' in the unsupervised sense?
- What is self-supervised learning and why does it matter?