PostGAN：一种基于GAN的后处理器，用于提高编码语音的质量
PostGAN: A GAN-Based Post-Processor to Enhance the Quality of Coded Speech
摘要：
通过变换编码进行编码的语音质量受到各种伪像的影响，特别是当用于消除频率分量的比特率变得太低时。为了减轻这些编码伪像并提高编码语音的质量，传统上在解码器侧采用依赖于从编码器发送的先验信息的后处理器。近年来，一些数据驱动的后后处理器已被提出，表现出优于传统的方法。在本文中，我们提出了PostGAN，这是一种基于GAN的神经后处理器，它在子带域中运行，依赖于U-Net架构和学习的仿射变换。它已在最近标准化的低复杂度，低延迟蓝牙编解码器（LC 3）的宽带语音在最低比特率（16 kbit/s）进行了测试。主观评价和客观分数表明，新引入的后处理器超过以前公布的方法，可以提高编码语音的质量约20个MUSHRA点。
英文摘要：
The quality of speech coded by transform coding is affected by various artefacts especially when bitrates to quantize the frequency components become too low. In order to mitigate these coding artefacts and enhance the quality of coded speech, a post-processor that relies on a-priori information transmitted from the encoder is traditionally employed at the decoder side. In recent years, several data-driven post-postprocessors have been proposed which were shown to outperform traditional approaches. In this paper, we propose PostGAN, a GAN-based neural post-processor that operates in the sub-band domain and relies on the U-Net architecture and a learned affine transform. It has been tested on the recently standardized low-complexity, low-delay bluetooth codec (LC3) for wideband speech at the lowest bitrate (16 kbit/s). Subjective evaluations and objective scores show that the newly introduced post-processor surpasses previously published methods and can improve the quality of coded speech by around 20 MUSHRA points.
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。
