通过单一超参数实现语音增强的延迟可调，兼顾质量与实时性。
Latency-Configurable Streaming Speech Enhancement via Asymmetric Temporal Padding
- 采用非对称时间填充和双缓冲机制，灵活配置延迟
- 12.5~75.0毫秒延迟下PESQ达3.35~3.43，12.5毫秒时超越此前最优
- 适合需要低延迟且高音质的实时语音处理场景
流式语音增强需在算法延迟与质量间权衡，现有方法多为因果与非因果的二选一。LaCo-SENet通过单个训练时超参数调控两种机制：首先，非对称时间填充重构卷积中的过去与未来上下文；其次，双缓冲流式架构结合状态缓冲（过去）与前瞻缓冲（输入与特征级未来），并引入选择性状态更新，防止未来帧泄漏，确保训练-推理一致性。在VoiceBank+DEMAND数据集上，固定预算（1.37M参数）的骨干模型支持12.5~75.0毫秒延迟，PESQ从3.35提升至3.43。在仅12.5毫秒（完全因果）时，PESQ达3.35，优于此前因果方案（3.27，46.5毫秒）。
原文摘要 · Abstract (English)
Streaming speech enhancement requires balancing algorithmic latency against quality, yet existing approaches largely treat this as a binary causal versus non-causal choice. LaCo-SENet addresses this issue with two mechanisms parameterized by a single training-time hyperparameter. First, asymmetric temporal padding redistributes past and future context in convolutions, enabling systematic latency configuration. Second, dual-buffer streaming combines state buffers for past context with lookahead buffers that supply future context at both the input and feature levels. Selective state updates also prevent future-frame leakage into the streaming state, ensuring training-inference consistency. On VoiceBank+DEMAND, a fixed-budget (1.37M parameters) backbone yields a family of models spanning 12.5-75.0 ms, with PESQ rising from 3.35 to 3.43. At just 12.5 ms (fully causal), a PESQ of 3.35 matches or exceeds the prior causal state-of-the-art (3.27 at 46.5 ms).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。