面向高效学习型语音压缩的帧级流式处理
Frame-Wise Streaming for Efficient Learned Speech Compression
AI总结：
本文针对现有学习型语音压缩模型缺乏流式支持的问题，提出StreamLSC模型，通过三大核心组件及可流式熵量化器实现流式处理，其性能与离线模型相当，获最优率失真结果及主观评估提升。
摘要：
语音压缩在实时通信、卫星通信等场景中愈发重要。神经编解码器在率失真（RD）性能上优于传统信号处理编解码器，带有长程依赖编解码器/解码器与熵模型的模型虽比卷积结构表现更优，但因依赖序列级关联仍缺乏流式支持。本文提出StreamLSC，这是一种基于流式网络三大核心组件（边界缓存因果卷积、帧内层归一化、RNN模式RWKV）的帧级流式学习型语音压缩模型，还集成了可流式熵量化器模块，在保证因果约束的同时实现高效上下文建模。实验表明，该流式模型性能与离线模型相当，达到了最先进的率失真结果，主观评估有显著提升，平均BD-RATE节省51.37%（ViSQOL）和53.99%（PESQ），BD-ViSQOL和BD-PESQ分别提升0.2154和0.5156。
英文摘要：
Speech compression is increasingly important in scenarios such as real-time and satellite communication. Neural codecs have shown superior Rate-Distortion (RD) performance over traditional signal-processing codecs. Models with long-range dependency encoders/decoders and entropy models outperform convolution-based structures, but they still lack streaming support since they rely on sequence-level correlations. In this paper, we propose StreamLSC, a frame-level streaming learned speech compression model built on three fundamental components of streaming networks, i.e. Boundary-Cached Causal Convolution, Intra-Frame Layer Normalization, and RNN-mode RWKV. Our model incorporates a streamable entropy quantizer module, ensuring efficient context model while preserving causal constraints. Experiments show that the streaming model achieves performance comparable to its offline counterpart, attaining state-of-the-art rate-distortion results, significant gains in subjective evaluations, -51.37% (ViSQOL) and -53.99% (PESQ) BD-RATE savings on average, and improvements of 0.2154 and 0.5156 in BD-ViSQOL and BD-PESQ.
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。
