通过后处理增强 whispered speech 的语音验证
Enhancing Speaker Verification with Whispered Speech via Post-Processing
AI总结：
本文提出一种模型，通过后处理增强 whispered speech 的语音验证性能，提升正常与whispered语音的识别准确率，达到98.16%的AUC，并在whispered语音对比中实现1.88%的EER。
摘要：
语音验证是通过分析语音确认个体身份的任务。whispered speech在声学特性上与phonated speech不同，会降低语音验证系统在现实场景中的性能，包括避免完全语音化以保护隐私、干扰他人或因疾病无法完全发声的情况。本文提出一个模型和训练方法，以获得更稳健的表示，以应对whispered speech的干扰。所提出的系统基于一个微调的语音验证主干网络，通过基于余弦相似度的分类和三元组损失进行联合优化。在正常语音与whispered语音试验中，相比基线（基线6.77% vs 我们5.27%）获得了22.26%的相对提升，达到98.16%的AUC。在whispered语音对比测试中，我们的模型实现了1.88%的EER，AUC为99.73%，比先前的ReDimNet-B2提升了15%。我们还总结了最流行和最先进的语音验证模型在whispered语音上的性能。此外，我们评估了这些模型在嘈杂音频下的表现，发现一般情况下，相同水平的噪声对whispered语音的语音验证性能影响比正常语音更显著。
英文摘要：
Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification systems in real-life scenarios, including avoiding fully phonated speech to protect privacy, disrupt others, or when the lack of full vocalization is dictated by a disease. In this paper we propose a model with a training recipe to obtain more robust representations against whispered speech hindrances. The proposed system employs an encoder--decoder structure built atop a fine-tuned speaker verification backbone, optimized jointly using cosine similarity--based classification and triplet loss. We gain relative improvement of 22.26\% compared to the baseline (baseline 6.77\% vs ours 5.27\%) in normal vs whispered speech trials, achieving AUC of 98.16\%. In tests comparing whispered to whispered, our model attains an EER of 1.88\% with AUC equal to 99.73\%, which represents a 15\% relative enhancement over the prior leading ReDimNet-B2. We also offer a summary of the most popular and state-of-the-art speaker verification models in terms of their performance with whispered speech. Additionally, we evaluate how these models perform under noisy audios, obtaining that generally the same relative level of noise degrades the performance of speaker verification more significantly on whispered speech than on normal speech.
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。
