arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1904.10380cs.SDeess.ASmath.SP
收藏

基于非平稳Gabor变换的谐波对齐帧模板及其在内容相关说话人比较中的应用

Harmonic-aligned Frame Mask Based on Non-stationary Gabor Transform with Application to Content-dependent Speaker Comparison

Acoustic Research Institute, Austrian Academy of Sciences(奥地利科学院声学研究所)

Feng Huang, Peter Balazs

摘要:

提出了一种基于非平稳Gabor变换的语音信号谐波对齐帧掩码算法。帧掩码对信号的传输系数进行操作,并因此将信号转换为对应信号。它描述了两个信号之间的差异。在以前的研究中,基于正则Gabor变换的帧模板被应用于单音符乐器声音分析。本研究将框架屏蔽方法扩展到语音信号。对于有声语音,基频通常随时间连续变化。我们采用NSGT与音高相关,因此随时间变化的频率分辨率,以达到谐波对齐的变换域,从而产生谐波对齐的帧掩码的语音信号。我们建议将谐波对齐的帧掩码应用于内容相关的说话人比较。该算法利用不同说话人的同一元音的浊音信号计算出的帧掩码作为相似性度量,对说话人身份进行比较和区分。使用深度神经网络获得的结果表明,所提出的帧掩码在表示说话人特征方面是有效的,并且在有限的数据场景中显示出SID应用的潜力。

英文摘要:

We propose harmonic-aligned frame mask for speech signals using non-stationary Gabor transform (NSGT). A frame mask operates on the transfer coefficients of a signal and consequently converts the signal into a counterpart signal. It depicts the difference between the two signals. In preceding studies, frame masks based on regular Gabor transform were applied to single-note instrumental sound analysis. This study extends the frame mask approach to speech signals. For voiced speech, the fundamental frequency is usually changing consecutively over time. We employ NSGT with pitch-dependent and therefore time-varying frequency resolution to attain harmonic alignment in the transform domain and hence yield harmonic-aligned frame masks for speech signals. We propose to apply the harmonic-aligned frame mask to content-dependent speaker comparison. Frame masks, computed from voiced signals of a same vowel but from different speakers, were utilized as similarity measures to compare and distinguish the speaker identities (SID). Results obtained with deep neural networks demonstrate that the proposed frame mask is valid in representing speaker characteristics and shows a potential for SID applications in limited data scenarios.

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。

↑