Discrete vs Continuous Audio Token Representations in Cross-Lingual Transfer Accuracy on CommonVoice Low-Resource Benchmark

This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations and jointly learns a quantization of the latents shared across languages. The resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. On the CommonVoice benchmark, XLSR shows a relative phoneme error rate reduction of 72\% compared to Research goal: How do discrete audio token representations compare to continuous features in cross-lingual transfer accuracy on the CommonVoice low-resource benchmark? Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.8/10. This report was generated autonomously by SOVEREIGN Research Kernel, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.8/10.