采用基于非自回归自注意力吸引子的逐帧流式端到端说话人日志分离
Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors
AI总结：
提出逐帧流式端到端说话人日志分离方法 FS-EEND，通过因果嵌入编码器、非自回归自注意力吸引子解码器和有限前瞻实现实时说话人检测与吸引子更新，并在低延迟、低成本下达到最先进性能。
摘要：
本工作以帧进帧出的方式提出了一种逐帧在线/流式端到端神经说话人日志分离方法 FS-EEND。为了逐帧检测数量灵活的说话人并提取/更新其对应的吸引子，我们提出利用因果说话人嵌入编码器和在线的基于非自回归自注意力的吸引子解码器。该方法采用前瞻机制，允许利用部分未来帧，从而实时有效地检测新说话人并自适应更新说话人吸引子。所提方法逐帧处理音频流，仅由前瞻帧带来较低的推理延迟。实验表明，与近期提出的基于块的在线方法相比，我们的 FS-EEND 方法取得了最先进的日志分离结果，同时具有较低的推理延迟和计算成本。
英文摘要：
This work proposes a frame-wise online/streaming end-to-end neural diarization (FS-EEND) method in a frame-in-frame-out fashion. To frame-wisely detect a flexible number of speakers and extract/update their corresponding attractors, we propose to leverage a causal speaker embedding encoder and an online non-autoregressive self-attention-based attractor decoder. A look-ahead mechanism is adopted to allow leveraging some future frames for effectively detecting new speakers in real time and adaptively updating speaker attractors. The proposed method processes the audio stream frame by frame, and has a low inference latency caused by the look-ahead frames. Experiments show that, compared with the recently proposed block-wise online methods, our method FS-EEND achieves state-of-the-art diarization results, with a low inference latency and computational cost.
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。
