arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.12085cs.SDcs.LGeess.AS
收藏

用于自监督说话人识别的增强对抗训练

Augmentation adversarial training for self-supervised speaker recognition

University of Oxford(牛津大学);Naver Corporation(Naver公司);Johns Hopkins University(约翰斯·霍普金斯大学)

Jaesung Huh, Hee Soo Heo, Jingu Kang, Shinji Watanabe, Joon Son Chung

摘要:

本文的目标是训练不需要说话人标签的鲁棒说话人识别模型。最近的无监督说话人表示的工作是基于对比学习,其中,他们鼓励内话语嵌入是相似的,跨话语嵌入是不同的。然而,由于话语内片段共享相同的声学特性,因此难以将说话者信息与声道信息分离。为此,我们提出了增强对抗训练策略,该策略训练网络对说话人信息具有辨别力,同时对所应用的增强保持不变。由于增强模拟了声学特性,因此训练网络对增强不变也鼓励网络对信道信息保持不变。在VoxCeleb和VOiCES数据集上进行的大量实验表明,与以前使用自我监督的作品相比,我们的自我监督模型的性能有了显着的改进,并且我们的自我监督模型的性能远远超过了人类。

英文摘要:

The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be similar and across-utterance embeddings to be dissimilar. However, since the within-utterance segments share the same acoustic characteristics, it is difficult to separate the speaker information from the channel information. To this end, we propose augmentation adversarial training strategy that trains the network to be discriminative for the speaker information, while invariant to the augmentation applied. Since the augmentation simulates the acoustic characteristics, training the network to be invariant to augmentation also encourages the network to be invariant to the channel information in general. Extensive experiments on the VoxCeleb and VOiCES datasets show significant improvements over previous works using self-supervision, and the performance of our self-supervised models far exceed that of humans.

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。

↑