Scholarlink

<p>With the fast-paced progress of deep learning, music source separation models have achieved impressive results. However, high separation quality often comes at the cost of complex architectures, limiting real-time performance. This study enhances singing voice separation by improving MMDenseNet and developing a real-time karaoke system that captures and separates accompaniment from played songs. We integrate traditional fundamental frequency (F0) estimation into complex ratio mask estimation, forming an integrated complex mask framework. On MUSDB18, we raise SDR from 3.87 dB to 6.44 dB over the original MMDenseNet (+ 2.57 dB absolute; +61% relative) while using only 0.33&#xa0;M parameters—the smallest among compared methods. To enable real-time applications, we redesign the model with a shallow neural network that learns from traditional F0 estimation. The final system achieves real-time throughput (RTF &lt; 1), e.g., 0.80 on an Intel i5-10500 PC and 0.88 on an NVIDIA Jetson AGX Xavier, demonstrating its potential for karaoke and related applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A lightweight real-time karaoke system with improved singing voice separation via fundamental frequency estimation integration

  • 期刊论文

  • 发表日期：

    2026年3月3日

查看全文
  • Tsung-Han Tsai,
  • Ling-Wei Wu

摘要

With the fast-paced progress of deep learning, music source separation models have achieved impressive results. However, high separation quality often comes at the cost of complex architectures, limiting real-time performance. This study enhances singing voice separation by improving MMDenseNet and developing a real-time karaoke system that captures and separates accompaniment from played songs. We integrate traditional fundamental frequency (F0) estimation into complex ratio mask estimation, forming an integrated complex mask framework. On MUSDB18, we raise SDR from 3.87 dB to 6.44 dB over the original MMDenseNet (+ 2.57 dB absolute; +61% relative) while using only 0.33 M parameters—the smallest among compared methods. To enable real-time applications, we redesign the model with a shallow neural network that learns from traditional F0 estimation. The final system achieves real-time throughput (RTF < 1), e.g., 0.80 on an Intel i5-10500 PC and 0.88 on an NVIDIA Jetson AGX Xavier, demonstrating its potential for karaoke and related applications.