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 2211.01461eess.AScs.CLcs.SD
收藏

基于自监督语音模型的音素分割

Phoneme Segmentation Using Self-Supervised Speech Models

University of Texas at Austin(德克萨斯大学奥斯汀分校)

Luke Strgar, David Harwath

摘要:

我们将迁移学习应用于音素分割任务,并展示了在自我监督预训练任务中学习到的表示的效用。我们的模型扩展了transformer风格的编码器,其中策略性地放置了卷积,这些卷积可以操纵在预训练中学习到的特征。使用TIMIT和七叶树语料库,我们训练和测试的监督和无监督设置的模型。后一种情况是通过提供一个有噪声的标签集与一个单独的模型的预测,它已经在一个无监督的方式训练。结果表明,我们的模型在两种设置和两个数据集上都超越了以前的最先进性能。最后,在发表的代码审查和尝试重现过去的分割结果的观察,我们发现有必要消除歧义的定义和广泛使用的评估指标的实现。我们解决这个模糊性划定两个不同的评价方案,并描述其细微差别。

英文摘要:

We apply transfer learning to the task of phoneme segmentation and demonstrate the utility of representations learned in self-supervised pre-training for the task. Our model extends transformer-style encoders with strategically placed convolutions that manipulate features learned in pre-training. Using the TIMIT and Buckeye corpora we train and test the model in the supervised and unsupervised settings. The latter case is accomplished by furnishing a noisy label-set with the predictions of a separate model, it having been trained in an unsupervised fashion. Results indicate our model eclipses previous state-of-the-art performance in both settings and on both datasets. Finally, following observations during published code review and attempts to reproduce past segmentation results, we find a need to disambiguate the definition and implementation of widely-used evaluation metrics. We resolve this ambiguity by delineating two distinct evaluation schemes and describing their nuances.

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。

↑