CCC-wav2vec 2.0：聚类辅助的跨对比自监督语音表示学习
CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations
AI总结：
提出ccc-wav2vec 2.0预训练策略，通过聚类降低相似负样本影响并结合跨对比损失，在LibriSpeech和Switchboard上分别实现最高15.6%和14.9%的相对WER改进。
摘要：
虽然自监督学习已经帮助从可用的未标记数据中获益于规模效应，但学习范式仍在不断改进。我们提出了一种名为 ccc-wav2vec 2.0 的新预训练策略，该策略使用聚类和基于增强的跨对比损失作为其自监督目标。通过聚类模块，我们降低了那些与正样本高度相似的负样本的影响。跨对比损失是在原始样本的编码器输出与其增强样本的量化器输出之间计算的，反之亦然，从而为预训练策略带来了鲁棒性。ccc-wav2vec 2.0 在 LibriSpeech 的 test-clean 和 test-other 集合上，相对于基线 wav2vec 2.0，分别实现了高达 15.6% 和 12.7% 的相对词错误率（WER）改进，且未使用任何语言模型。所提出的方法在 Switchboard 数据上进行微调时，相对于基线 wav2vec 2.0 也实现了高达 14.9% 的相对 WER 改进。我们将所有代码公开发布在 GitHub 上。
英文摘要：
While Self-Supervised Learning has helped reap the benefit of the scale from the available unlabeled data, the learning paradigms are continuously being bettered. We present a new pre-training strategy named ccc-wav2vec 2.0, which uses clustering and an augmentation-based cross-contrastive loss as its self-supervised objective. Through the clustering module, we scale down the influence of those negative examples that are highly similar to the positive. The Cross-Contrastive loss is computed between the encoder output of the original sample and the quantizer output of its augmentation and vice-versa, bringing robustness to the pre-training strategy. ccc-wav2vec 2.0 achieves up to 15.6% and 12.7% relative WER improvement over the baseline wav2vec 2.0 on the test-clean and test-other sets, respectively, of LibriSpeech, without the use of any language model. The proposed method also achieves up to 14.9% relative WER improvement over the baseline wav2vec 2.0 when fine-tuned on Switchboard data. We make all our codes publicly available on GitHub.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
