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 2401.08342eess.AS
收藏

ECAPA2:一种用于鲁棒说话人嵌入的混合神经网络架构与训练策略

ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings

Jenthe Thienpondt, Kris Demuynck

AI总结:

本文提出混合神经网络架构ECAPA2及相应训练策略,通过分析现有说话人验证模型并结合对重叠语音和短语音的鲁棒性训练,在VoxCeleb1上以更少参数取得最先进性能,并公开预训练模型。

摘要:

在本文中,我们提出了ECAPA2,一种新颖的混合神经网络架构和训练策略,用于生成鲁棒的说话人嵌入。大多数说话人验证模型基于一维或二维卷积运算,通常分别表现为时延神经网络或ResNet。混合模型相对未被充分探索,且缺乏关于其架构选择最佳实践的直观解释。我们通过对当前说话人验证架构的分析来论证本文提出的ECAPA2模型。此外,我们提出了一种训练策略,使说话人嵌入对重叠语音和短语音段长度更加鲁棒。所提出的ECAPA2架构和训练策略在VoxCeleb1测试集上取得了最先进的性能,且参数量显著少于当前模型。最后,我们公开了一个预训练模型,以促进下游任务的研究。

英文摘要:

In this paper, we present ECAPA2, a novel hybrid neural network architecture and training strategy to produce robust speaker embeddings. Most speaker verification models are based on either the 1D- or 2D-convolutional operation, often manifested as Time Delay Neural Networks or ResNets, respectively. Hybrid models are relatively unexplored without an intuitive explanation what constitutes best practices in regard to its architectural choices. We motivate the proposed ECAPA2 model in this paper with an analysis of current speaker verification architectures. In addition, we propose a training strategy which makes the speaker embeddings more robust against overlapping speech and short utterance lengths. The presented ECAPA2 architecture and training strategy attains state-of-the-art performance on the VoxCeleb1 test sets with significantly less parameters than current models. Finally, we make a pre-trained model publicly available to promote research on downstream tasks.

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。

↑