Pitch Restoration for Robust Speech Recognition

机译：音调恢复以实现可靠的语音识别

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

This article suggests a based spectral normalization method, which purpose is to alleviate both the changing on peaks structure and on the flat zones of the speech spectrum, caused by additive noise. The proposed spectral normalization can be viewed as a noise estimate done in a frame by frame basis by assuming the clean database as lightly corrupted. This noise estimate is then used to restore both the peaked and the flat spectral zones of the speech spectrum. This algorithm was implemented over a baseline spectral normalisation method, which purpose is to emphasize the robustness in the regions of less energy of the speech spectrum, since in these regions the noise is more dominant.

机译：本文提出了一种基于频谱的归一化方法，其目的是减轻由加性噪声引起的峰值结构和语音频谱平坦区域的变化。通过假设干净的数据库轻微损坏，可以将建议的频谱归一化视为在逐帧的基础上进行的噪声估计。然后，该噪声估计将用于恢复语音频谱的峰值频谱区域和平坦频谱区域。该算法是在基线频谱归一化方法之上实施的，其目的是强调语音频谱能量较小的区域中的鲁棒性，因为在这些区域中，噪声更为占优势。

著录项

来源
《6th International Workshop on Computational Processing of the Portuguese Language PROPOR 2003 Jun 26-27, 2003 Faro, Portugal》|2003年|p.18-22|共5页
会议地点 Faro(PT);Faro(PT)
作者
Carlos Lima; Adriano Tavares; Carlos Silva;
展开▼
作者单位

Department of Industrial Electronics of University of Minho, Campus de Azurem 4800-058 Guimaraes, Portugal;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类自然科学研究方法;
关键词

相似文献

外文文献
中文文献
专利

1. Robust Speech Spectra Restoration against Unspecific Noise Conditions for Pitch Detection [J] . Xin XU, Noboru HAYASAKA, Yoshikazu MIYANAGA IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences . 2008,第3期

机译：针对非特定噪声条件的健壮语音频谱恢复，用于音调检测
2. Feature Extraction Based on Pitch-Synchronous Averaging for Robust Speech Recognition [J] . Morales-Cordovilla J. A., Peinado A. M., Sanchez V., Audio, Speech, and Language Processing, IEEE Transactions on . 2011,第3期

机译：基于音高同步平均的特征提取用于鲁棒语音识别
3. An effect of pitch fluctuation on noise-robust speech recognition [J] . Kiyoaki Aikawa, Kentaro Ishizuka 電子情報通信学会技術研究報告. 音声. Speech . 2001,第522期

机译：音高波动对鲁棒语音识别的影响
4. Pitch Restoration for Robust Speech Recognition [C] . Carlos Lima, Adriano Tavares, Carlos Silva International Workshop on Computational Processing of the Portuguese Language . 2003

机译：强大的演讲识别的音高恢复
5. Robust speech processing based on microphone array, audio-visual, and frame selection for in-vehicle speech recognition and in-set speaker recognition. [D] . Zhang, Xianxian. 2005

机译：基于麦克风阵列，视听和帧选择的强大语音处理功能，可实现车载语音识别和内置说话人识别。
6. On Dynamic Pitch Benefit for Speech Recognition in Speech Masker [O] . Jing Shen, Pamela E. Souza -1

机译：语音掩盖器中语音识别的动态音高效益研究
7. A PITCH BASED NOISE ESTIMATION TECHNIQUE FOR ROBUST SPEECH RECOGNITION WITH MISSING DATA [O] . Juan A. Morales-cordovilla, Ning Ma, Victoria Sánchez, 2012

机译：缺少数据的基于螺距的鲁棒语音识别噪声估计技术
8. Robust Speech Processing & Recognition: Speaker ID, Language ID, Speech Recognition/Keyword Spotting, Diarization/Co-Channel/Environmental Characterization, Speaker State Assessment. [R] . Hansen, J. H. 2015

机译：强大的语音处理和识别：说话者ID，语言ID，语音识别/关键字识别，Diarization / Co-Channel /环境表征，说话者状态评估。

Pitch Restoration for Robust Speech Recognition

摘要

著录项

相似文献

相关主题

期刊订阅