Generalized Source-Filter Structures for Speech Synthesis

机译：语音合成的通用源过滤器结构

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this paper we discuss various digital filter principles as models for synthetic speech generation. Warped linear prediction (WLP) and frequency-warped filters have been introduced earlier as a method to reduce the filter order in high-quality wideband speech synthesis. In addition to analyzing WLP and frequency-warped filters we introduce new related structures and techniques for arbitrary frequency resolution allocation. Kautz filters can be considered as generalized structures for pole-zero modeling. This study focuses on residual-excited synthesis and diphone-oriented reconstruction of speech signals. Control strategies for text-to-speech synthesis are discussed briefly.

机译：在本文中，我们讨论了各种数字滤波器原理，作为合成语音生成的模型。较早引入弯曲线性预测（WLP）和频率扭曲滤波器作为降低高质量宽带语音合成中滤波器阶数的方法。除了分析WLP和频率扭曲滤波器之外，我们还介绍了用于任意频率分辨率分配的新的相关结构和技术。 Kautz滤波器可以视为零极点建模的广义结构。这项研究的重点是语音信号的残留激励合成和面向双音素的重建。简要讨论了文本到语音合成的控制策略。

著录项

来源
《European Conference on Speech Communication and Technology v.3; 20010903-20010907; Aalborg; DK》|2001年|P.2271-2274|共4页
会议地点 Aalborg(DK);Aalborg(DK)
作者
Matti Karjalainen; Tuomas Paatero;
展开▼
作者单位

Helsinki University of Technology Laboratory of Acoustics and Audio Signal Processing P.O. Box 3000, FIN-02015 HUT, Espoo, Finland;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类传播理论;
关键词

相似文献

外文文献
中文文献
专利

1. Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis [J] . Xin Wang, Shinji Takaki, Junichi Yamagishi Audio, Speech, and Language Processing, IEEE/ACM Transactions on . 2020,第期

机译：神经源 - 滤波器波形模型用于统计参数语音合成
2. Robust speech analysis-synthesis method based on the source-filter model and its applications [J] . Takahiro Ohtsuka, Hideki Kasuya 電子情報通信学会技術研究報告. 音声. Speech . 2001,第87期

机译：基于源滤波器模型的鲁棒语音分析综合方法及其应用
3. Robust speech analysis-synthesis method based on the source-filter model and its applications [J] . Takahiro Ohtsuka, Hideki Kasuya 電子情報通信学会技術研究報告. 音声. Speech . 2001,第87期

机译：基于源滤波器模型及其应用的鲁棒语音分析合成方法
4. Generalized Source-Filter Structures for Speech Synthesis [C] . Matti Karjalainen, Tuomas Paatero European conference on speech communication and technology . 2001

机译：语音合成的广义源滤波器结构
5. Most likely state sequence speech reconstruction using a generalized hidden semi Markov model with two distinct regeneration times applied to English. [D] . Moore, Michael D. 2004

机译：最可能的状态序列语音重构是使用广义隐式半马尔可夫模型进行的，其中两个不同的再生时间应用于英语。
6. Early Interactive Acoustic Experience with Non-speech Generalizes to Speech and Confers a Syllabic Processing Advantage at 9 Months [O] . Silvia Ortiz-Mantilla, Teresa Realpe-Bonilla, April A Benasich -1

机译：早期的非语音互动声学经验可以使语音普遍化并在9个月时赋予音节处理优势
7. Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis [O] . Xin Wang, Shinji Takaki, Junichi Yamagishi 2020

机译：神经源 - 滤波器波形模型用于统计参数语音合成

Generalized Source-Filter Structures for Speech Synthesis

摘要

著录项

相似文献

相关主题

期刊订阅