本文件规定了一种统一的语音和音频编解码器，能够对语音和音频内容任意混合的信号进行编码。该编解码器的性能可与最知名的编码技术相媲美，或优于该技术，该技术可能专门针对语音或一般音频内容的编码进行定制。编解码器支持高比特率的单通道和多通道编码，并提供感知透明的质量。同时，它能够以非常低的比特率实现非常高效的编码，同时保留完整的音频带宽。 本文档结合了以前的MPEG标准中开发的几种基于感知的压缩技术:感知成形量化噪声、上频谱区域的参数编码和立体声舞台的参数编码。然而，它很好地结合了这些- 已知的感知技术和信源编码技术:声音产生的模型，特别是人类语音的模型。

This document specifies a unified speech and audio codec which is capable of coding signals having an arbitrary mix of speech and audio content. The codec has a performance comparable to, or better than, the best known coding technology that might be tailored specifically to coding of either speech or general audio content. The codec supports single and multi-channel coding at high bitrates and provides perceptually transparent quality. At the same time, it enables very efficient coding at very low bitrates while retaining the full audio bandwidth. This document incorporates several perceptually-based compression techniques developed in previous MPEG standards: perceptually shaped quantization noise, parametric coding of the upper spectrum region and parametric coding of the stereo sound stage. However, it combines these well-known perceptual techniques with a source coding technique: a model of sound production, specifically that of human speech.