BriefGPT.xyz
Oct, 2017
基于深度神经网络的端到端优化语音编码
End-to-End Optimized Speech Coding with Deep Neural Networks
HTML
PDF
Srihari Kankanahalli
TL;DR
该论文介绍了一种基于深度神经网络的语音编码器，它实现了从原始语音数据到压缩、量化、熵编码和解压缩的端到端优化，无需手动特征工程，并在不同的比特率下表现与AMR-WB标准相当，同时能够在3.8GhZ英特尔CPU上实时运行。
Abstract
Modern
compression
algorithms are often the result of laborious domain-specific research; industry standards such as MP3, JPEG, and
amr-wb
took years to develop and were largely hand-designed. We present a deep <
→