专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US06678657B1 Method and apparatus for a robust feature extraction for speech recognition 有权
标题翻译：用于语音识别的鲁棒特征提取的方法和装置
公开(公告)号：US06678657B1
公开(公告)日：2004-01-13
申请号：US09694617
申请日：2000-10-23
申请人： Raymond Brückner , Hans-Günter Hirsch , Rainer Klisch , Volker Springer
发明人： Raymond Brückner , Hans-Günter Hirsch , Rainer Klisch , Volker Springer
IPC分类号： G10L1502
CPC分类号： G10L15/20 , G10L15/02 , G10L21/0208
摘要： The present invention relates to a method and an apparatus for a robust feature extraction for speech recognition in a noisy environment, wherein the speech signal is segmented and is characterized by spectral components. The speech signal is splitted into a number of short term spectral components in L subbands, with L=1, 2, . . . and a noise spectrum from segments that only contain noise is estimated. Then a spectral subtraction of the estimated noise spectrum from the corresponding short term spectrum is performed and a probability for each short term spectrum component to contain noise is calculated. Finally these spectral component of each short-term spectrum, having a low probability to contain speech are interpolated in order to smooth those short-term, spectra that only contain noise. With the interpolation the spectral components containing noise are interpolated by reliable spectral speech components that could be found in the neighborhood.
摘要翻译：本发明涉及一种用于在噪声环境中进行语音识别的鲁棒特征提取的方法和装置，其中语音信号被分段并且由频谱分量表征。语音信号分为L个子带中的多个短期频谱分量，其中L = 1,2。。。并且估计仅包含噪声的段的噪声频谱。然后，对相应的短期频谱进行估计噪声频谱的频谱减法，并计算每个短期频谱分量包含噪声的概率。最后，对包含语音的低概率的每个短期频谱的这些频谱分量进行插值，以平滑那些仅包含噪声的短期谱图。通过插值，包含噪声的频谱成分被可靠的光谱语音分量内插，该分量可以在邻域中找到。

2. 发明授权

US07062431B2 Speech analyzing stage and method for analyzing a speech signal 有权
标题翻译：用于分析语音信号的语音分析阶段和方法
公开(公告)号：US07062431B2
公开(公告)日：2006-06-13
申请号：US10046536
申请日：2002-01-16
申请人： Hans-Günter Hirsch , Volker Springer , Rainer Klisch , Karl Hellwig
发明人： Hans-Günter Hirsch , Volker Springer , Rainer Klisch , Karl Hellwig
IPC分类号： G10L15/00 , G10L19/00
CPC分类号： G10L15/02
摘要： A speech analyzing stage (12) and a method for analyzing a speech signal is described. The speech analyzing stage (12) is part of an automatic speech recognition system (10) and is adapted for analyzing in the spectral domain a speech signal sampled at one of at least two different system sampling rates. The speech analyzing stage (12) comprises a first spectral analyzer (18a) for analyzing the speech signal up to a first frequency (flowest) which is preferably derived from the lowest system sampling rate (2×flowest) and a second spectral analyzer (18b) for analyzing the speech signal at least above the first frequency (flowest).
摘要翻译：描述语音分析阶段（12）和分析语音信号的方法。语音分析阶段（12）是自动语音识别系统（10）的一部分，并且适于在频谱域中分析以至少两种不同系统采样率之一采样的语音信号。语音分析阶段（12）包括用于分析语音信号的第一频谱分析器（18a），直到第一频率（f SUB最低），其优选地从最低系统采样速率（2xf < SUB>最低）和第二频谱分析器（18b），用于分析至少高于第一频率（f SUB最低）的语音信号。

3. 发明授权

US07415411B2 Method and apparatus for generating acoustic models for speaker independent speech recognition of foreign words uttered by non-native speakers 有权
标题翻译：用于产生用于由非母语发音者发出的外来语言的独立语音识别的声学模型的方法和装置
公开(公告)号：US07415411B2
公开(公告)日：2008-08-19
申请号：US10793072
申请日：2004-03-04
申请人： Klaus Reinhard , Jochen Junkawitsch , Andreas Kieβling , Rainer Klisch
发明人： Klaus Reinhard , Jochen Junkawitsch , Andreas Kieβling , Rainer Klisch
IPC分类号： G10L15/00
CPC分类号： G10L15/063 , G10L15/187 , G10L2015/025
摘要： Acoustic models for speech recognition are automatically generated utilizing trained acoustic models from a native language and a foreign language. A phoneme-to-phoneme mapping is utilized to enable the description of foreign language words with native language phonemes. The phoneme-to-phoneme mapping is used for training foreign language words, described by native language phonemes on foreign language speech material. A new phonetic lexicon is created containing foreign language words and native language words transcribed by native language phonemes. Robust native language acoustic models can be derived utilizing foreign language and native language training material. The mapping may be used for training a grapheme to phoneme transducer (i.e., foreign language to native language) to generate native language pronunciations for new foreign language words.
摘要翻译：使用来自母语和外语的训练声学模型自动生成用于语音识别的声学模型。使用音素到音素映射来描述具有母语音素的外语单词。音素到音素映射用于训练用外语言材料的母语音素描述的外语单词。创建一个新的语音词典，其中包含由母语音素转录的外语单词和母语单词。可以利用外语和母语培训材料推导出鲁棒的母语声学模型。该映射可以用于训练字母到音素换能器（即外语到母语），以产生新的外语单词的本地语言发音。

4. 发明申请

US20050197835A1 Method and apparatus for generating acoustic models for speaker independent speech recognition of foreign words uttered by non-native speakers 有权
标题翻译：用于产生用于由非母语发音者发出的外来语言的独立语音识别的声学模型的方法和装置
公开(公告)号：US20050197835A1
公开(公告)日：2005-09-08
申请号：US10793072
申请日：2004-03-04
申请人： Klaus Reinhard , Jochen Junkawitsch , Andreas Kiessling , Rainer Klisch
发明人： Klaus Reinhard , Jochen Junkawitsch , Andreas Kiessling , Rainer Klisch
IPC分类号： G10L15/02 , G10L15/06 , G10L15/18 , G10L15/00
CPC分类号： G10L15/063 , G10L15/187 , G10L2015/025
摘要： Acoustic models for speech recognition are automatically generated utilizing trained acoustic models from a native language and a foreign language. A phoneme-to-phoneme mapping is utilized to enable the description of foreign language words with native language phonemes. The phoneme-to-phoneme mapping is used for training foreign language words, described by native language phonemes on foreign language speech material. A new phonetic lexicon is created containing foreign language words and native language words transcribed by native language phonemes. Robust native language acoustic models can be derived utilizing foreign language and native language training material. The mapping may be used for training a grapheme to phoneme transducer (i.e., foreign language to native language) to generate native language pronunciations for new foreign language words.
摘要翻译：使用来自母语和外语的训练声学模型自动生成用于语音识别的声学模型。使用音素到音素映射来描述具有母语音素的外语单词。音素到音素映射用于训练用外语言材料的母语音素描述的外语单词。创建一个新的语音词典，其中包含由母语音素转录的外语单词和母语单词。可以利用外语和母语培训材料推导出鲁棒的母语声学模型。该映射可以用于训练字母到音素换能器（即外语到母语），以产生新的外语单词的本地语言发音。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式