Speech separation study reveals SI-SDR limitations with noisy references

Researchers have investigated the effectiveness of the Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) in speech separation when training data includes noisy references. Their analysis revealed that noise in references can limit achievable SI-SDR and introduce unwanted noise into separated outputs. To mitigate this, they proposed a method to enhance references and augment training data, which showed reduced noise but also potential for processing artifacts. AI

影响 Highlights limitations in current speech separation metrics, potentially guiding future research in audio AI.

排序理由 This is a research paper detailing a study on a specific metric within speech separation. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Libri2Mix
• NISQA.v2
• Scale-Invariant Signal-to-Distortion Ratio
• Simon Dahl Jepsen
• SI-SDR
• WHAM!
• WSJ0-2Mix

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →