论文标题
通过目标扬声器提取和神经不确定性估计来改善RNN传感器
Improving RNN Transducer With Target Speaker Extraction and Neural Uncertainty Estimation
论文作者
论文摘要
宣传者的语音识别旨在识别具有背景噪音和干扰扬声器的嘈杂环境中的目标扬声器语音。这项工作提出了一个联合框架，该框架结合了时间域目标扬声器语音提取和复发性神经网络传感器（RNN-T）。为了稳定联合培训，我们提出了一种多阶段训练策略，该策略在联合培训之前预先培训和微型调节模块。同时，提出了说话者的身份和语音增强不确定性度量，以补偿目标语音提取模块中的残余噪声和伪影。与对目标语音提取模型进行微调的识别器相比，我们的实验表明，添加神经不确定性模块可显着降低具有背景噪声的多演讲者信号的17％相对性格错误率（CER）。多条件实验表明，我们的方法可以在嘈杂条件下实现9％的相对性能增益，同时保持在清洁条件下的性能。
Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech extraction and Recurrent Neural Network Transducer (RNN-T). To stabilize the joint-training, we propose a multi-stage training strategy that pre-trains and fine-tunes each module in the system before joint-training. Meanwhile, speaker identity and speech enhancement uncertainty measures are proposed to compensate for residual noise and artifacts from the target speech extraction module. Compared to a recognizer fine-tuned with a target speech extraction model, our experiments show that adding the neural uncertainty module significantly reduces 17% relative Character Error Rate (CER) on multi-speaker signals with background noise. The multi-condition experiments indicate that our method can achieve 9% relative performance gain in the noisy condition while maintaining the performance in the clean condition.
