首页> 外文OA文献 >Robust Features for Speaker-Independent Speech Recognition Based on a Certain Class of Translation-Invariant Transformations ⋆

【2h】

Robust Features for Speaker-Independent Speech Recognition Based on a Certain Class of Translation-Invariant Transformations ⋆

机译：基于某类翻译不变变换的与说话人无关的语音识别的鲁棒特征⋆

页面导航

著录项
引文网络
相似文献
相关主题

著录项

作者
Florian Müller; Alfred Mertins;
展开▼
作者单位

展开▼
年度 2013
总页数
原文格式 PDF
正文语种
中图分类

相似文献

外文文献
中文文献
专利

1. Acoustic Model Training Using Pseudo-Speaker Features Generated by MLLR Transformations for Robust Speaker-Independent Speech Recognition [J] . Arata ITOH, Sunao HARA, Norihide KITAOKA, IEICE transactions on information and systems . 2012,第10期

机译：使用由MLLR转换生成的伪扬声器特征进行声学模型训练，以实现与扬声器无关的可靠语音识别
2. Acoustic Model Training Using Pseudo-Speaker Features Generated by MLLR Transformations for Robust Speaker-Independent Speech Recognition [J] . Arata ITOH, Sunao HARA, Norihide KITAOKA, IEICE Transactions on Information and Systems . 2012,第10期

机译：使用由MLLR转换生成的伪扬声器特征进行声学模型训练，以实现与扬声器无关的可靠语音识别
3. Cepstral domain segmental nonlinear feature transformations for robust speech recognition [J] . Segura J.C., Benitez C., de la Torre A., IEEE signal processing letters . 2004,第5期

机译：倒谱域分段非线性特征变换，用于鲁棒语音识别
4. Robust Features for Speaker-Independent Speech Recognition Based on a Certain Class of Translation-Invariant Transformations [C] . Florian Muller, Alfred Mertins International Conference on Advances in Nonlinear Speech Processing . 2010

机译：扬声器独立语音识别的强大功能基于一类翻译不变变换
5. Design of loss functions and feature transformation for minimum classification error based automatic speech recognition [D] . Ratnagiri, Madhavi Vedula 2011

机译：基于最小分类误差的自动语音识别损失函数设计和特征变换
6. A Multistream Feature Framework Based on Bandpass Modulation Filtering for Robust Speech Recognition [O] . Sridhar Krishna Nemala, Kailash Patil, Mounya Elhilali -1

机译：在带通滤波调制多流功能根据框架鲁棒语音识别
7. Acoustic Model Training Using Pseudo-Speaker Features Generated by MLLR Transformations for Robust Speaker-Independent Speech Recognition [O] . Arata Itoh, Sunao Hara, Norihide Kitaoka, 2012

机译：使用由MLLR转换生成的伪扬声器特征进行声学模型训练，以实现与扬声器无关的可靠语音识别
8. Spire Based Speaker-Independent Continuous Speech Recognition Using Mixed Feature Sets [R] . Dawson, R. G. 1987

机译：基于混合特征集的基于尖端的扬声器无关连续语音识别

Robust Features for Speaker-Independent Speech Recognition Based on a Certain Class of Translation-Invariant Transformations ⋆

著录项

引文网络

相似文献

相关主题

期刊订阅