arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.00991eess.AScs.CLcs.SD
收藏

时域语音表征的数据增强对比学习

Data Augmenting Contrastive Learning of Speech Representations in the Time Domain

Facebook AI Research(脸书人工智能研究院);EHESS(法国高等社会科学研究院);CNRS(法国国家科学研究中心);INRIA(法国国家信息与自动化研究所);ENS-PSL University(巴黎高等师范学院-巴黎文理研究大学)

Eugene Kharitonov, Morgane Rivière, Gabriel Synnaeve, Lior Wolf, Pierre-Emmanuel Mazaré, Matthijs Douze, Emmanuel Dupoux

摘要:

对比预测编码(CPC)是一种基于过去语音段预测未来语音段的编码方法,是语音信号表示学习的有效算法。然而,它在无监督的评估基准上仍然表现不佳。在这里,我们介绍了WavAugment,一个时域数据增强库,并发现在过去应用增强通常是更有效的,并产生更好的性能比其他方法。我们发现,音调修改,加性噪声和混响的组合大大提高了CPC的性能(相对提高18-22%),用少600倍的数据击败了参考Libri-light结果。使用域外数据集,时域数据增强可以推动CPC在2017年零语音基准测试中达到最先进水平。我们还表明,时域数据增强一贯提高下游有限监督音素分类任务的12-15%相对的一个因素。

英文摘要:

Contrastive Predictive Coding (CPC), based on predicting future segments of speech based on past segments is emerging as a powerful algorithm for representation learning of speech signal. However, it still under-performs other methods on unsupervised evaluation benchmarks. Here, we introduce WavAugment, a time-domain data augmentation library and find that applying augmentation in the past is generally more efficient and yields better performances than other methods. We find that a combination of pitch modification, additive noise and reverberation substantially increase the performance of CPC (relative improvement of 18-22%), beating the reference Libri-light results with 600 times less data. Using an out-of-domain dataset, time-domain data augmentation can push CPC to be on par with the state of the art on the Zero Speech Benchmark 2017. We also show that time-domain data augmentation consistently improves downstream limited-supervision phoneme classification tasks by a factor of 12-15% relative.

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。

↑