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 2403.06404cs.SDcs.LGeess.AS
收藏

面向神经说话人嵌入的带不确定性余弦评分

Cosine Scoring with Uncertainty for Neural Speaker Embedding

The Hong Kong Polytechnic University(香港理工大学)

Qiongqiong Wang, Kong Aik Lee

AI总结:

针对传统余弦评分无法处理说话人嵌入不确定性的问题,本文提出前端不确定性估计并传播至后端余弦评分的方法,在 VoxCeleb 和 SITW 上显著降低 EER 与 minDCF。

摘要:

说话人表示中的不确定性建模旨在学习语音话语中存在的变异性。尽管传统的余弦评分计算高效且在说话人识别中广泛使用,但它缺乏处理不确定性的能力。为应对这一挑战,本文提出一种在说话人嵌入前端估计不确定性并将其传播到余弦评分后端的方法。在 VoxCeleb 和 SITW 数据集上进行的实验证实了所提方法在处理由嵌入估计产生的不确定性方面的有效性。与传统余弦相似度相比,该方法实现了性能提升,EER 和 minDCF 分别平均降低 8.5% 和 9.8%。它在实际应用中也具有较高的计算效率。

英文摘要:

Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to handle uncertainty. To address this challenge, this paper proposes an approach for estimating uncertainty at the speaker embedding front-end and propagating it to the cosine scoring back-end. Experiments conducted on the VoxCeleb and SITW datasets confirmed the efficacy of the proposed method in handling uncertainty arising from embedding estimation. It achieved improvement with 8.5% and 9.8% average reductions in EER and minDCF compared to the conventional cosine similarity. It is also computationally efficient in practice.

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。

↑