| 声音转换技术的研究与进展 |
| |
| 引用本文： | 左国玉,刘文举,阮晓钢.声音转换技术的研究与进展[J].电子学报,2004,32(7):1165-1172. |
| |
| 作者姓名： | 左国玉 刘文举 阮晓钢 |
| |
| 作者单位： | 1. 中科院自动化所模式识别国家重点实验室,北京 100080;2. 北京工业大学电子信息与控制工程学院,北京 100022 |
| |
| 基金项目： | 国家自然科学基金，北京市自然科学基金 |
| |
| 摘 要： | 声音转换是一项改变说话人声音特征的技术,可以将一人的语音模式转换为与其特性不同的另一人语音模式.声音转换算法的目标是确定一个什么样的模式转换规则,使转换语音保持第一个说话人原有语音信息内容不变,而具有第二个说话人的声音特点.本文介绍了当前声音转换技术领域的研究状态,主要分析现有声音转换技术中各种转换算法的实现原理,描述声音转换系统性能的各种评估方法,最后给出了对声音转换技术的简要评述和展望.
|
| 关 键 词： | 声音转换 语音频谱 基频曲线 声门激励 码本映射 人工神经网络 高斯混合模型 隐马尔科夫模型 |
| 文章编号： | 0372-2112(2004)07-1165-08 |
| 收稿时间： | 2002-12-13 |
Voice Conversion Technology and Its Development |
| |
| ZUO Guo yu ,LIU Wen ju ,RUAN Xiao gang.Voice Conversion Technology and Its Development[J].Acta Electronica Sinica,2004,32(7):1165-1172. |
| |
| Authors: | ZUO Guo yu LIU Wen ju RUAN Xiao gang |
| |
| Institution: | 1. National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100080,China;2. School of Electronics Information and Control Engineering,Beijing University of Technology,Beijing 100022,China |
| |
| Abstract: | Voice conversion technology transforms one person's speech pattern into another pattern with distinct characteristics.The goal of a voice conversion algorithm is to achieve a transformation that makes the speech of the first speaker sounds as though it were uttered by the second speaker giving it a new identity,while preserving the original meaning.This paper introduces some current studies on voice conversion technology,which focus on various types of algorithms implemented in voice conversion area.Different evaluation methods for voice conversion performance are described.A technological outlook for this speech technique is given in the last section. |
| |
| Keywords: | voice conversion speech spectrum pitch contour glottal excitation codebook mapping artificial neural network Gaussian mixture model hidden Markov model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
| 点击此处可从《电子学报》下载免费的PDF全文 |
