speaker identification

According to the task, it is composed of two parts speaker verification and speaker identification.

从具体应用的角度可将声纹识别分为说话人辨认和说话人确认两类，从识别条件的角度可将其分为与文本有关的说话人识别和与文本无关的说话人识别两类。

A Method Based On Multiple Vector Quantization For Robust Text-independent Speaker Identification

噪声背景下基于多模板矢量量化的与文本无关的话者辩识

They are Vector Quantization ( VQ), Hidden Markov Models ( HMM) and Gaussian Mixture Models ( GMM) speaker identification respectively.

采用的方法分别是矢量量化（VQ）识别方法、隐马尔可夫模型（HMM）识别方法、高斯混合模型（GMM）识别方法。

A novel method is proposed to trained VQ codebook for HMM-based speaker identification. The codebook is trained based on the criterion of making each codeword in the codebook to share training vectors equally.

提出了一种新的适用于离散HMM说话人辨认系统的VQ码本训练方法，码本的训练准则是使码本中各码字的利用率趋于均等。

A text-independent speaker identification system based on SVMs was implemented and the results showed good performance.

用支持向量机实现了一个与文本无关的说话人辨认系统，实验表明，本方法有良好的效果。

An Automatic Speaker Identification System Based on Serial Decision Method

基于序贯判决法的自动说话人识别

Vector Quantization ( VQ ) is one of the popular codebook design methods for text-independent speaker identification.

矢量量化 ( VQ ) 方法是文本无关说话人识别中广泛应用的建模方法之一,它的主要问题是码本设计问题.

Adding Phoneme Duration Information to Spectral Model in Speaker Identification

添加音素持续时间信息到频谱模型的说话人辨认研究

In order to improve the robustness and identification rate of the system, hierarchical speaker identification is proposed. Then the likeliness of GMM classifier is weighted by using the Gauss probability density of the pitch and novel likeliness is proposed for speaker identification.

为了提高系统的鲁棒性和辨识率，在采用分级说话人辨识的基础上，将基音周期的高斯概率密度对GMM分类器的似然度进行加权，形成新的似然度进行说话人辨识。

An inter-speaker information ANN method is proposed, analyzing GMM model speaker identification system performance, and a hybrid GMM/ ANN speaker identification system is structured.

通过分析GMM（高斯混合模型）的说话人辨认系统的性能，提出了一种捕捉不同说话人交互信息的人工神经网络（ANN）方法，构成一个GMM/ANN混合说话人辨认系统。

Speaker Identification Algorithm of Semi-Supervised Learning Mechanism

半监督学习机制下的说话人辨认算法

Efficient Training of MCE for Speaker Identification

基于MCE训练算法的说话人辨认系统