arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.07045eess.AScs.SD
收藏

基于克隆网络的显著语音表示

Salient Speech Representations Based on Cloned Networks

Google LLC.(谷歌有限责任公司);Victoria University of Wellington(惠灵顿维多利亚大学)

W. Bastiaan Kleijn, Felicia S. C. Lim, Michael Chinen, Jan Skoglund

摘要:

我们将显着特征定义为系统设计者定义为等效的信号所共享的特征。该定义允许设计者提供定性信息。我们的目标是找到显着的功能,是有用的条件生成网络。我们通过联合训练编码器网络的一组克隆来提取显著特征。每个网络克隆接收来自一组等效信号的不同信号作为输入。目标函数鼓励网络克隆将其输入映射到一组在克隆中相同的特征。它还鼓励特征独立性,并且可选地,通过解码器重建期望的目标信号。作为一个应用程序,我们训练一个系统,提取语音的特征向量的时间序列,并使用它作为一个条件的WaveNet生成系统,促进编码和增强。

英文摘要:

We define salient features as features that are shared by signals that are defined as being equivalent by a system designer. The definition allows the designer to contribute qualitative information. We aim to find salient features that are useful as conditioning for generative networks. We extract salient features by jointly training a set of clones of an encoder network. Each network clone receives as input a different signal from a set of equivalent signals. The objective function encourages the network clones to map their input into a set of features that is identical across the clones. It additionally encourages feature independence and, optionally, reconstruction of a desired target signal by a decoder. As an application, we train a system that extracts a time-sequence of feature vectors of speech and uses it as a conditioning of a WaveNet generative system, facilitating both coding and enhancement.

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。

↑