VoiceExtender：基于引导扩散模型的短语音文本无关说话人验证
VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model
AI总结：
针对短语音下说话人验证性能下降的问题，提出VoiceExtender架构，通过内置与外置两种说话人嵌入引导的扩散模型增强语音特征，在VoxCeleb1数据集不同短语音时长下均实现等错误率的显著相对提升。
摘要：
说话人验证（SV）的性能会随着语音时长缩短而下降。针对这一问题，我们提出了一种名为VoiceExtender的新架构，为提升短时长语音信号处理场景下的SV性能提供了可行方案。我们采用两种引导扩散模型：内置说话人嵌入（SE）引导扩散模型和外置说话人嵌入引导扩散模型，二者均使用基于扩散模型的样本生成器，借助SE引导基于短语音增强语音特征。在VoxCeleb1数据集上的大量实验结果表明，我们的方法优于基线模型：在0.5秒、1.0秒、1.5秒和2.0秒的短语音条件下，等错误率（EER）的相对提升幅度分别为46.1%、35.7%、10.4%和5.7%。
英文摘要：
Speaker verification (SV) performance deteriorates as utterances become shorter. To this end, we propose a new architecture called VoiceExtender which provides a promising solution for improving SV performance when handling short-duration speech signals. We use two guided diffusion models, the built-in and the external speaker embedding (SE) guided diffusion model, both of which utilize a diffusion model-based sample generator that leverages SE guidance to augment the speech features based on a short utterance. Extensive experimental results on the VoxCeleb1 dataset show that our method outperforms the baseline, with relative improvements in equal error rate (EER) of 46.1%, 35.7%, 10.4%, and 5.7% for the short utterance conditions of 0.5, 1.0, 1.5, and 2.0 seconds, respectively.
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。
