arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.02742eess.AScs.AIcs.SD
收藏

深度说话人嵌入结构中的残留信息

Residual Information in Deep Speaker Embedding Architectures

Technical University of Cluj-Napoca(克卢日-纳波卡技术大学)

Adriana Stan

摘要:

说话人嵌入表示从语音信号中提取代表性矢量表示的手段,使得表示仅与说话人身份有关。嵌入通常用于分类和区分不同的扬声器。然而,没有客观的措施来评估说话人嵌入的能力,以解开从其他语音特征的说话人身份。这意味着嵌入远非理想,高度依赖于训练语料库,并且仍然包括与诸如语言内容、记录条件或话语的说话风格等因素有关的一定程度的残留信息。本文介绍了对使用一些最新和高性能DNN架构提取的六组说话人嵌入的分析,特别是它们能够真正从语音信号中分离说话人身份的程度。为了正确地评估架构,使用大型多扬声器并行语音数据集。该数据集包括46个说话者发出相同的提示,记录在专业工作室或他们的家庭环境中。分析着眼于内和扬声器间的相似性措施计算在不同的嵌入集,以及如果简单的分类和回归方法能够提取几个残留的信息因素的扬声器嵌入。结果表明,所分析的嵌入的辨别能力是非常高的,但在所有的分析架构,剩余信息仍然存在于表示的形式,一个高度相关的记录条件,语言内容和话语持续时间。

英文摘要:

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate between different speakers. However, there is no objective measure to evaluate the ability of a speaker embedding to disentangle the speaker identity from the other speech characteristics. This means that the embeddings are far from ideal, highly dependent on the training corpus and still include a degree of residual information pertaining to factors such as linguistic content, recording conditions or speaking style of the utterance. This paper introduces an analysis over six sets of speaker embeddings extracted with some of the most recent and high-performing DNN architectures, and in particular, the degree to which they are able to truly disentangle the speaker identity from the speech signal. To correctly evaluate the architectures, a large multi-speaker parallel speech dataset is used. The dataset includes 46 speakers uttering the same set of prompts, recorded in either a professional studio or their home environments. The analysis looks into the intra- and inter-speaker similarity measures computed over the different embedding sets, as well as if simple classification and regression methods are able to extract several residual information factors from the speaker embeddings. The results show that the discriminative power of the analyzed embeddings is very high, yet across all the analyzed architectures, residual information is still present in the representations in the form of a high correlation to the recording conditions, linguistic contents and utterance duration.

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。

↑