dnn+i-vector在kaldi中的实现。

在说话人识别系统中，大多数现有技术是基于i-vector，其核心思想是将语音数据的高维统计特性映射到低维表示（即i-vector），然后利用概率线性判别分析（PLDA）分类器进行比较，从而判定是否为同一说话人。...

Kaldi用于ivector和xvector的摘要 文件清单 ivector/ conf/ ：为mfcc和vad配置文件 wav/ ：测试音频（您也可以使用自己的wav路径，请参阅步骤1 ） 仅支持flac（安装flac），wav和sph（安装sph2pipe） model_3000h/ ：预训练模型 enroll.sh ：主进程enroll.sh data/ ：保存提取的特征（已生成文件） utt2spk, wav.scp通过make_data.py生成两个文件 spk2utt ：从utt2spk生成 log/ ：保存所有日志 tmp/ ：保存所有tmp文件 xvector/ c

基于i-vector的说话人识别系统， 内部含有 - ./doc/ this directory contains a documention on how to generate i-vectors - ./gmm/ directory used to store the Universal Background Model - ./iv/ directory used to store the i-vectors when extracted - ./mat/ directory used to store matrix objects - ./ndx/ directory used to store index files

提出了一种将基于深度神经网络（Deep Neural Network，DNN）特征映射的回归分析模型应用到身份认证矢量（identity vector，i-vector）/概率线性判别分析（Probabilistic Linear Discriminant Analysis，PLDA）说话人系统模型中的方法。DNN通过拟合含噪语音和纯净语音i-vector之间的非线性函数关系，得到纯净语音i-vector的近似表征，达到降低噪声对系统性能影响的目的。在TIMIT数据集上的实验验证了该方法的可行性和有效性。

MSR Identity Toolbox: A Matlab Toolbox for Speaker Recognition Research Version 1.0 Seyed Omid Sadjadi, Malcolm Slaney, and Larry Heck Microsoft Research, Conversational Systems Research Center (CSRC) [email protected], {mslaney,larry.heck}@microsoft.com This report serves as a user manual for the tools available in the Microsoft Research (MSR) Identity Toolbox. This toolbox contains a collection of Matlab tools and routines that can be used for research and development in speaker recognition. It provides researchers with a test bed for developing new front-end and back-end techniques, allowing replicable evaluation of new advancements. It will also help newcomers in the field by lowering the “barrier to entry”, enabling them to quickly build baseline systems for their experiments. Although the focus of this toolbox is on speaker recognition, it can also be used for other speech related applications such as language, dialect and accent identification. In recent years, the design of robust and effective speaker recognition algorithms has attracted significant research effort from academic and commercial institutions. Speaker recognition has evolved substantially over the past 40 years; from discrete vector quantization (VQ) based systems to adapted Gaussian mixture model (GMM) solutions, and more recently to factor analysis based Eigenvoice (i-vector) frameworks. The Identity Toolbox provides tools that implement both the conventional GMM-UBM and state-of-the-art i-vector based speaker recognition strategies. A speaker recognition system includes two primary components: a front-end and a back-end. The front-end transforms acoustic waveforms into more compact and less redundant representations called acoustic features. Cepstral features are most often used for speaker recognition. It is practical to only retain the high signal-to-noise ratio (SNR) regions of the waveform, therefore there is also a need for a speech activity detector (SAD) in the fr