Description: 常用的说话人识别方法有模板匹配法、统计建模法、联接主义法(即人工神经网络实现)。考虑到数据量、实时性以及识别率的问题，采用基于矢量量化和隐马尔可夫模型(HMM)相结合的方法。
说话人识别的系统主要由语音特征矢量提取单元(前端处理)、训练单元、识别单元和后处理单元组成，
-Commonly used methods of speaker recognition template matching method, statistical modeling method, and connection method (ie, artificial neural networks). Taking into account the amount of data, real-time as well as the recognition rate of the problem, based on vector quantization and Hidden Markov Model (HMM) method of combining. Speaker recognition system mainly by the voice feature vector extraction unit (front-end treatment), training modules, identification and post-treatment unit modules, Platform: |
Size: 64512 |
Author:孙丽 |
Hits:
Description: This paper presents a hybrid framework of feature extraction and hidden Markov modeling (HMM) for two-dimensional pattern recognition. Importantly, we explore a new discriminative training criterion to assure model compactness and discriminability. This criterion is derived from the hypothesis test theory via maximizing the confidence of accepting the hypothesis that observations are from target HMM states rather than competing HMM states. Accordingly, we develop the maximum confidence hidden Markov modeling (MC-HMM) for face recognition. Platform: |
Size: 52224 |
Author:rupesh |
Hits:
Description: 通过基于HMM的语音识别系统的基本结构,详细介绍了语音信号采集、预处理、MFCC特征参数提取、HMM训练和HMM识别等主要模块的基本原理 并针对实际应用中HMM存在的模型初始化和数据溢出等问题进行分析,引入了一些能提高系统性能的相应措施。-By the basic structure of HMM-based speech recognition system, details the basic principles of audio signal acquisition, preprocessing, MFCC feature extraction, HMM training and HMM recognition and other major modules and for the model initialization exist in the practical application of HMM and data overflow and other issues are analyzed, we introduced some measures to improve system performance. Platform: |
Size: 1096704 |
Author:David |
Hits:
Search - feature extraction by hmm model