发表机构
Paderborn University（帕德博恩大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出自监督方法学习房间冲激响应嵌入，用于在混响和噪声环境中提升语音增强性能，并在所有指标上取得一致改进。
AI 中文摘要
我们提出了一种自监督方法，用于从单通道带噪混响语音中学习房间冲激响应（RIR）表示。该方法首先在混响数据上训练，然后在带噪混响数据上训练，最后采用教师-学生方法，其中学生模型在给定混响输入的带噪版本时，学习复制教师模型的嵌入。我们通过从这些嵌入中估计声学房间参数来评估其表示能力。将判别式语音增强模型基于这些嵌入进行条件化处理，在所有评估指标（包括下游词错误率）上均取得了一致的性能提升，对混响和带噪混响语音均有效。
英文摘要
We propose a self-supervised approach for learning room impulse response (RIR) representations from single-channel noisy-reverberant speech. It consists of first training on reverberant data, then on noisy-reverberant data, and finally with a teacher-student approach, where the student learns to replicate the teacher's embeddings when given a noisy version of the reverberant input. We assess their representational capabilities by estimating acoustic room parameters from them. Conditioning a discriminative speech enhancement model on the derived embeddings yields consistent gains across all evaluated metrics, including downstream word error rate, for both reverberant and noisy-reverberant speech.
CommentsSubmitted to ICASSP 2027
