基于音素的子带贡献提取言语特征的说话人识别研究-计算机技术专业论文.docx

ABSTRACT In this paper, we employed the phoneme mean F-ratio method to investigate the different contributions of different frequency region from the point of view of Chinese phoneme, and apply it for speaker identification. It is found that the speaker individual information depending on the phonemes is distributed in different frequency regions of speech sound. Based on the contribution rate, we extracted the new features and combined with GMM model. Compared with the MFCC feature, the identification error rate with the proposed feature was reduced by 32.94%. Then, we conduct morphological analysis and acoustic modeling of the nasal and paranasal cavities to investigate the effects of the nasal cavity on speaker characteristics. Morphological analysis showed that the nasal cavity possesses relatively large variation across speakers. Acoustic effects results showed that the inter-speaker variation of the nasal tract affects spectra in the frequency range from 2 kHz to 4 kHz, which is in agreement with the results from our previous statistical studies. In speech production, the function of the velum is not a binary switch of on and off. For the nasalized vowels and voiced stops in Japanese, the radiation probably mainly results from velum vibration. two mechanical experiments were conducted to reveal the acoustic incorporation of the transvelar coupling of the yielding velum. Finally, an acoustic model was proposed to integrate the velum effect for the speech sounds. KEY WORDS：Speaker identification, Feature extraction, Nasal tract, Paranasal sinuses, Velum vibration 目 录 HYPERLINK \l _bookmark0 第一章 绪 论1 HYPERLINK \l _bookmark1 1.1 研究背景 1 HYPERLINK \l _bookmark2 1.1.1 说话人识别介绍 1 HYPERLINK \l _bookmark3 1.1.2 说话人识别优势与应用前景 2 HYPERLINK \l _bookmark4 1.2 研究进展 4 HYPERLINK \l _bookmark5 1.2.1 国内外研究现状 4 HYPERLINK \l _bookmark6 1.2.2 存在的问题 5 HYPERLINK \l _bookmark7 1.3 论文研究主要内容 6 HYPERLINK \l _bookmark8 1.4 论文研究结构安排 7 HYPERLINK \l _bookmark9 第二章 说话人的个性特征分析8 HYPE