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 2211.00854cs.LGcs.SDeess.AS
收藏

更多的演讲者还是更多的演讲者?

More Speaking or More Speakers?

Apple(苹果公司)

Dan Berrebbi, Ronan Collobert, Navdeep Jaitly, Tatiana Likhomanenko

摘要:

自训练(ST)和自监督学习(SSL)方法在自动语音识别(ASR)中已经证明了强大的改进。尽管取得了这些进展,但据我们所知,没有分析这些方法中使用的标记和未标记数据集的组成如何影响结果。在这项工作中,我们的目标是分析最近的SSL算法(wav2vec 2.0)和最近的ST算法(slimIPL)的训练数据中的扬声器的数量的效果。我们通过改变发言者的数量,同时保持小时数固定,对标记和未标记的数据进行系统分析,反之亦然。我们的研究结果表明,SSL需要大量的未标记的数据,以产生高精度的结果,而ST需要足够数量的扬声器在标记的数据,特别是在低制度设置。以这种方式,这两种方法提高了监督学习在不同制度的数据组成。

英文摘要:

Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR). In spite of these advances, to the best of our knowledge, there is no analysis of how the composition of the labelled and unlabelled datasets used in these methods affects the results. In this work we aim to analyse the effect of number of speakers in the training data on a recent SSL algorithm (wav2vec 2.0), and a recent ST algorithm (slimIPL). We perform a systematic analysis on both labeled and unlabeled data by varying the number of speakers while keeping the number of hours fixed and vice versa. Our findings suggest that SSL requires a large amount of unlabeled data to produce high accuracy results, while ST requires a sufficient number of speakers in the labelled data, especially in the low-regime setting. In this manner these two approaches improve supervised learning in different regimes of data composition.

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。

↑