arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.10399eess.AScs.LGcs.SD
收藏

使用深度神经网络快速计算响度

Fast computation of loudness using a deep neural network

University of Cambridge(剑桥大学)

Josef Schlittenlacher, Richard E. Turner, Brian C. J. Moore

摘要:

本文介绍了一种深度神经网络(DNN),用于从声音的时间波形预测声音的瞬时响度。DNN使用一个更复杂的模型的输出进行训练,称为剑桥响度模型。虽然现代PC可以使用剑桥响度模型每秒执行几百次响度计算,但使用DNN每秒可以执行超过100,000次,允许实时计算响度。使用这两个模型的瞬时响度水平的预测之间的均方根偏差小于0.5 phon看不见的类型的声音。我们认为,通过更快的DNN模拟复杂感知模型的一般方法可以应用于其他感知模型,使它们实时运行。

英文摘要:

The present paper introduces a deep neural network (DNN) for predicting the instantaneous loudness of a sound from its time waveform. The DNN was trained using the output of a more complex model, called the Cambridge loudness model. While a modern PC can perform a few hundred loudness computations per second using the Cambridge loudness model, it can perform more than 100,000 per second using the DNN, allowing real-time calculation of loudness. The root-mean-square deviation between the predictions of instantaneous loudness level using the two models was less than 0.5 phon for unseen types of sound. We think that the general approach of simulating a complex perceptual model by a much faster DNN can be applied to other perceptual models to make them run in real time.

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。

↑