基于重编程与后端学习的高效黑盒说话人验证模型自适应
Efficient Black-Box Speaker Verification Model Adaptation with Reprogramming and Backend Learning
AI总结：
针对说话人验证中的语言域不匹配问题，本文提出黑盒重编程结合轻量梯度估计与两层后端学习的自适应方法，以低计算和参数成本达到接近或优于完全微调的效果。
摘要：
近年来，深度神经网络（DNN）的发展显著提升了说话人验证（SV）系统的性能。然而，在实际应用中部署基于 DNN 的 SV 系统时，域不匹配仍是一个持续存在的关键问题。为缓解这种不匹配导致的性能下降，域自适应变得十分必要。本文受对抗重编程概念启发，提出一种通过操控可学习模型输入来自适应基于 DNN 的 SV 模型的方法。预训练 SV 模型保持固定，并且仅在前向过程中发挥作用，类似于一个黑盒模型。该方法使用一个轻量级网络估计输入端可学习参数的梯度，从而绕过通过黑盒模型进行的梯度反向传播。重编程后的输出由一个两层后端学习模块处理，作为最终自适应后的说话人嵌入。在本文设计中，参与梯度计算的参数量很少。凭借少量额外参数，所提方法同时实现了内存效率和参数效率。实验在语言不匹配场景下进行。在计算成本大幅降低的情况下，所提方法在实验中取得了与完全微调模型接近甚至更优的性能，证明了其有效性。
英文摘要：
The development of deep neural networks (DNN) has significantly enhanced the performance of speaker verification (SV) systems in recent years. However, a critical issue that persists when applying DNN-based SV systems in practical applications is domain mismatch. To mitigate the performance degradation caused by the mismatch, domain adaptation becomes necessary. This paper introduces an approach to adapt DNN-based SV models by manipulating the learnable model inputs, inspired by the concept of adversarial reprogramming. The pre-trained SV model remains fixed and functions solely in the forward process, resembling a black-box model. A lightweight network is utilized to estimate the gradients for the learnable parameters at the input, which bypasses the gradient backpropagation through the black-box model. The reprogrammed output is processed by a two-layer backend learning module as the final adapted speaker embedding. The number of parameters involved in the gradient calculation is small in our design. With few additional parameters, the proposed method achieves both memory and parameter efficiency. The experiments are conducted in language mismatch scenarios. Using much less computation cost, the proposed method obtains close or superior performance to the fully finetuned models in our experiments, which demonstrates its effectiveness.
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。
