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 2309.09220eess.AScs.AIcs.SD
收藏

通过自监督嵌入和增强的声道变量改进语音逆向映射

Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables

Institute for Systems Research(系统研究所);University of Maryland(马里兰大学)

Ahmed Adel Attia, Yashish M. Siriwardena, Carol Espy-Wilson

AI总结:

本文面向声学至发音器官的语音逆向映射,结合 HuBERT 等自监督语音表示与改进几何变换生成的声道变量,将 PPMC 从 0.7452 提升至 0.8141。

摘要:

深度学习模型的性能在很大程度上取决于其高效编码输入特征并将其解码为有意义输出的能力。更好的输入与输出表示有望提升模型的性能和泛化能力。在声学至发音器官的语音逆向映射(SI)系统背景下,我们研究了使用通过自监督学习(SSL)模型获得的语音表示(例如 HuBERT)相较于传统声学特征的影响。此外,我们研究了通过改进的几何变换模型纳入新的声道变量(TVs)。通过结合这两种方法,我们将用于评估 SI 系统声道变量估计准确性的 Pearson 积矩相关系数(PPMC)得分从 0.7452 提升至 0.8141,提高了 6.9%。我们的研究结果强调,来自 SSL 模型的丰富特征表示以及面向目标声道变量的改进几何变换,对增强 SI 系统功能具有深远影响。

英文摘要:

The performance of deep learning models depends significantly on their capacity to encode input features efficiently and decode them into meaningful outputs. Better input and output representation has the potential to boost models' performance and generalization. In the context of acoustic-to-articulatory speech inversion (SI) systems, we study the impact of utilizing speech representations acquired via self-supervised learning (SSL) models, such as HuBERT compared to conventional acoustic features. Additionally, we investigate the incorporation of novel tract variables (TVs) through an improved geometric transformation model. By combining these two approaches, we improve the Pearson product-moment correlation (PPMC) scores which evaluate the accuracy of TV estimation of the SI system from 0.7452 to 0.8141, a 6.9% increase. Our findings underscore the profound influence of rich feature representations from SSL models and improved geometric transformations with target TVs on the enhanced functionality of SI systems.

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。

↑