Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation

Non-autoregressive Transformers (NATs) are recently applied in direct speech-tospeech translation systems, which convert speech across different languages without intermediate text data. Although NATs generate high-quality outputs and offer faster inference than autoregressive models, they tend to produce incoherent and repetitive results due to complex data distribution (e.g., acoustic and linguistic variations in speech).