轻量级流式语音超分辨率模型，实时处理无延迟。
StreamWSR: Streamable and Lightweight Waveform-Domain Neural Speech Super-Resolution
- 全因果结构+帧级波形表示，支持零前瞻流式推理。
- 仅900万参数、20亿浮点运算，性能优于主流方法。
- 适合低延迟语音增强场景，如实时通话与语音助手。
本文提出 StreamWSR，一种可流式处理的波形域语音超分辨率模型。采用全因果架构与紧凑的帧级波形表示，实现零前瞻流式推理，无需声码器重建或显式相位预测。StreamWSR 通过步长因果卷积将输入波形下采样为紧凑的帧级表示，再利用轻量级因果长短时建模主干，在因果约束下捕捉局部波形结构与长程历史依赖。最后，通过因果转置卷积将建模输出还原至波形域，并通过残差连接与输入波形融合，生成最终高分辨率语音。在16 kHz语音超分辨率任务上，实验表明，StreamWSR 在语音质量与可懂度方面达到或超越代表性波形与谱域基线方法，同时保持零前瞻流式优势，仅需900万参数和20亿浮点运算。
原文摘要 · Abstract (English)
This paper proposes StreamWSR, a Streamable neural Waveform-domain model for speech Super-Resolution (SR). By adopting a fully causal architecture with compact frame-level waveform representation, the proposed StreamWSR supports zero-look-ahead streaming inference while avoiding vocoder-based reconstruction and explicit phase prediction. Specifically, StreamWSR downsamples the input waveform into a compact frame-level representation using strided causal convolutions. Then, a lightweight causal long-short-term modeling backbone is employed to capture both local waveform structures and long-range historical dependencies under causal constraints. Finally, the modeled output is converted back to the waveform domain through a causal transposed-convolution and combined with the input waveform via a residual connection to generate the final high-resolution speech. Experimental results on 16 kHz speech SR show that StreamWSR achieves competitive or superior speech quality and intelligibility compared with representative waveform- and spectrum-based baselines, while maintaining a zero-look-ahead streaming advantage with only 9M parameters and 2G FLOPs.
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。