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. 发明申请

US20100312564A1 LOCAL AND REMOTE FEEDBACK LOOP FOR SPEECH SYNTHESIS 有权
标题翻译：语音合成的本地和远程反馈环
公开(公告)号：US20100312564A1
公开(公告)日：2010-12-09
申请号：US12479007
申请日：2009-06-05
申请人： Michael D. Plumpe
发明人： Michael D. Plumpe
IPC分类号： G10L13/08
CPC分类号： G10L13/033 , G10L13/08 , H04M3/493 , H04M2201/39
摘要： A local text to speech feedback loop is utilized to modify algorithms used in speech synthesis to provide a user with an improved experience. A remote text to speech feedback loop is utilized to aggregate local feedback loop data and incorporate best solutions into new improved text to speech engine for deployment.
摘要翻译：利用本地文本到语音反馈回路来修改语音合成中使用的算法，为用户提供改进的体验。利用远程文本到语音反馈回路来聚合局部反馈回路数据，并将最佳解决方案纳入到新的改进的文本到语音引擎中进行部署。

2. 发明授权

US06502066B2 System for generating formant tracks by modifying formants synthesized from speech units 有权
标题翻译：通过修改从语音单元合成的共振峰来产生共振峰轨迹的系统
公开(公告)号：US06502066B2
公开(公告)日：2002-12-31
申请号：US09824142
申请日：2001-04-02
申请人： Michael D. Plumpe
发明人： Michael D. Plumpe
IPC分类号： G10L1902
CPC分类号： G10L19/06 , G10L25/15 , G10L2025/906
摘要： Formants, corresponding to input speech units based either on a known text or the results of a speech recognition procedure, are generated from a formant synthesizer. A frequency response is generated based on the synthesized formants. A second frequency response is generated based on a speech signal which is received and which corresponds to utterances of speech units. The synthesized formants are modified based on a comparison of the frequency response corresponding to the synthesized formants and specific proportional characteristics of a frequency response of the input speech signal. In one illustrative embodiment, the comparison is then recalculated and further modifications are made accordingly to improve accuracy. In one illustrative embodiment, time aligning and frequency warping are utilized as modification functions.
摘要翻译：从共振峰合成器产生对应于基于已知文本的输入语音单元或语音识别过程的结果的共形函数。基于合成共振峰产生频率响应。基于接收的对应于语音单元的话语的语音信号来生成第二频率响应。基于对应于合成共振峰的频率响应和输入语音信号的频率响应的特定比例特性的比较，对合成的共振峰进行修改。在一个说明性实施例中，然后重新计算比较，并相应地进行进一步修改以提高精度。在一个说明性实施例中，时间对准和频率翘曲被用作修改功能。

3. 发明授权

US07133826B2 Method and apparatus using spectral addition for speaker recognition 失效
公开(公告)号：US07133826B2
公开(公告)日：2006-11-07
申请号：US11065573
申请日：2005-02-24
申请人： Xuedong Huang , Michael D. Plumpe
发明人： Xuedong Huang , Michael D. Plumpe
IPC分类号： G10L15/08
CPC分类号： G10L17/20 , G10L17/04 , G10L21/0216
摘要： A method and apparatus for speaker recognition is provided that matches the noise in training data to noise in testing data using spectral addition. Under spectral addition, the mean and variance for a plurality of frequency components are adjusted in the training data and the test data so that each mean and variance is matched in a resulting matched training signal and matched test signal. The adjustments made to the training data and test data add to the mean and variance of the training data and test data instead of subtracting from the mean and variance.

4. 发明授权

US06876966B1 Pattern recognition training method and apparatus using inserted noise followed by noise reduction 有权
标题翻译：模式识别训练方法和装置采用插入噪声，然后降噪
公开(公告)号：US06876966B1
公开(公告)日：2005-04-05
申请号：US09688950
申请日：2000-10-16
申请人： Li Deng , Xuedong Huang , Michael D. Plumpe
发明人： Li Deng , Xuedong Huang , Michael D. Plumpe
IPC分类号： G06K9/62 , G10L15/06 , G10L15/20 , G10L21/02
CPC分类号： G10L21/0208 , G06K9/6256 , G10L15/06 , G10L15/20 , G10L21/0216
摘要： A method and apparatus for training and using a pattern recognition model are provided. Under the invention, additive noise that matches noise expected in a test signal is included in a training signal. The noisy training signal is passed through one or more noise reduction techniques to produce pseudo-clean training data. The pseudo-clean training data is used to train the pattern recognition model. When the test signal is received, it is passed through the same noise reduction techniques used on the noisy training signal. This produces pseudo-clean test data, which is applied to the pattern recognition model. Under one embodiment, sets of training data are produced with each set containing a different type of noise.
摘要翻译：提供了一种用于训练和使用模式识别模型的方法和装置。根据本发明，与训练信号中预期的噪声相匹配的附加噪声包括在训练信号中。噪声训练信号通过一个或多个降噪技术来产生伪清理训练数据。伪清理训练数据用于训练模式识别模型。当接收到测试信号时，它通过与噪声训练信号相同的降噪技术。这产生了伪清理测试数据，该数据应用于模式识别模型。在一个实施例中，产生训练数据集，每组包含不同类型的噪声。

5. 发明授权

US08442826B2 Application-dependent information for recognition processing 有权
标题翻译：用于识别处理的应用依赖信息
公开(公告)号：US08442826B2
公开(公告)日：2013-05-14
申请号：US12481612
申请日：2009-06-10
申请人： Jonathan E. Hamaker , Julian James Odell , Michael D. Plumpe , Sandeep Manocha , Keith C. Herold
发明人： Jonathan E. Hamaker , Julian James Odell , Michael D. Plumpe , Sandeep Manocha , Keith C. Herold
IPC分类号： G10L15/00
CPC分类号： G10L15/197
摘要： Architecture for integrating application-dependent information into a constraints component at deployment time or when available. In terms of a general grammar, the constraints component can include or be a general grammar that comprises application-independent information and is structured in such a way that application-dependent information can be integrated into the general grammar without loss of fidelity. The general grammar includes a probability space and reserves a section of the probability space for the integration of application-dependent information. An integration component integrates the application-dependent information into the reserved section of the probability space for recognition processing. The application-dependent information is integrated into the reserved section of the probability space at deployment time or when available. The general grammar is structured to support the integration and improve the overall system.
摘要翻译：用于将应用程序相关信息集成到部署时间或可用时的约束组件的体系结构。在一般语法方面，约束组件可以包括或作为包含应用程序无关信息的通用语法，并且以这样的方式构造，使得依赖于应用程序的信息可以被集成到通用语法中而不会失去保真度。一般语法包括概率空间，并且保留用于集成应用依赖信息的概率空间的一部分。集成部件将应用相关信息集成到用于识别处理的概率空间的保留部分中。应用相关信息在部署时或可用时被集成到概率空间的保留部分中。一般语法的结构是支持整合和改进整体系统。

6. 发明授权

US07949536B2 Intelligent speech recognition of incomplete phrases 有权
标题翻译：智能语音识别不完整的短语
公开(公告)号：US07949536B2
公开(公告)日：2011-05-24
申请号：US11513772
申请日：2006-08-31
申请人： David Mowatt , Ricky Loynd , Robert Edward Dewar , Rachel Imogen Morton , Qiang Wu , Robert Ian Brown , Michael D. Plumpe , Philipp Heinz Schmid
发明人： David Mowatt , Ricky Loynd , Robert Edward Dewar , Rachel Imogen Morton , Qiang Wu , Robert Ian Brown , Michael D. Plumpe , Philipp Heinz Schmid
IPC分类号： G10L21/00
CPC分类号： G10L15/193 , G10L2015/223
摘要： Intelligent speech recognition is used to provide users with the ability to utter more user friendly commands. Satisfaction is increased when a user can vocalize a subset of a formal command name and still have the intended command identified and processed. Moreover, greater accuracy in identifying a command application from a user's utterance can be achieved by ignoring command choices associated with unlikely user utterances. An intelligent speech recognition system can identify differing acceptable verbal command phrase forms, e.g., but not limited to, complete commands, command subsequences and command subsets, for different commands supported by the system. Subset blocking words are identified for assistance in reducing the ambiguity in matching user verbal command phrases with valid commands supported by the intelligent speech recognition system.
摘要翻译：智能语音识别用于为用户提供更多用户友好命令的能力。当用户能够发出正式命令名称的子集并且仍然具有识别和处理的预期命令时，满意度就会增加。此外，通过忽略与不太可能的用户话语相关联的命令选择，可以实现从用户的话语识别命令应用程序的更高精度。智能语音识别系统可以识别用于系统支持的不同命令的不同的可接受的口头命令短语形式，例如但不限于完整的命令，命令子序列和命令子集。识别子集阻塞字以帮助减少用户语言命令短语与由智能语音识别系统支持的有效命令的模糊性。

7. 发明授权

US07571097B2 Method for training of subspace coded gaussian models 失效
标题翻译：训练子空间编码高斯模型的方法
公开(公告)号：US07571097B2
公开(公告)日：2009-08-04
申请号：US10388260
申请日：2003-03-13
申请人： Alejandro Acero , Michael D. Plumpe
发明人： Alejandro Acero , Michael D. Plumpe
IPC分类号： G10L15/14 , G10L15/06
CPC分类号： G10L15/144 , G10L15/285
摘要： A method for compressing multiple dimensional gaussian distributions with diagonal covariance matrixes includes clustering a plurality of gaussian distributions in a multiplicity of clusters for each dimension. Each cluster can be represented by a centroid having a mean and a variance. A total decrease in likelihood of a training dataset is minimized for the representation of the plurality of gaussian distributions.
摘要翻译：用对角协方差矩阵压缩多维高斯分布的方法包括针对每个维度在多个簇中聚类多个高斯分布。每个簇可以由具有平均值和方差的质心来表示。对于多个高斯分布的表示，训练数据集的可能性的总的降低被最小化。

8. 发明申请

US20080059186A1 Intelligent speech recognition of incomplete phrases 有权
标题翻译：智能语音识别不完整的短语
公开(公告)号：US20080059186A1
公开(公告)日：2008-03-06
申请号：US11513772
申请日：2006-08-31
申请人： David Mowatt , Ricky Loynd , Robert Edward Dewar , Rachel Imogen Morton , Qiang Wu , Robert Ian Brown , Michael D. Plumpe , Philipp Heinz Schmid
发明人： David Mowatt , Ricky Loynd , Robert Edward Dewar , Rachel Imogen Morton , Qiang Wu , Robert Ian Brown , Michael D. Plumpe , Philipp Heinz Schmid
IPC分类号： G10L15/18
CPC分类号： G10L15/193 , G10L2015/223
摘要： Intelligent speech recognition is used to provide users with the ability to utter more user friendly commands. Satisfaction is increased when a user can vocalize a subset of a formal command name and still have the intended command identified and processed. Moreover, greater accuracy in identifying a command application from a user's utterance can be achieved by ignoring command choices associated with unlikely user utterances. An intelligent speech recognition system can identify differing acceptable verbal command phrase forms, e.g., but not limited to, complete commands, command subsequences and command subsets, for different commands supported by the system. Subset blocking words are identified for assistance in reducing the ambiguity in matching user verbal command phrases with valid commands supported by the intelligent speech recognition system.
摘要翻译：智能语音识别用于为用户提供更多用户友好命令的能力。当用户能够发出正式命令名称的子集并且仍然具有识别和处理的预期命令时，满意度就会增加。此外，通过忽略与不太可能的用户话语相关联的命令选择，可以实现从用户的话语识别命令应用程序的更高精度。智能语音识别系统可以识别用于系统支持的不同命令的不同的可接受的口头命令短语形式，例如但不限于完整的命令，命令子序列和命令子集。识别子集阻塞字以帮助减少用户语言命令短语与由智能语音识别系统支持的有效命令的模糊性。

9. 发明授权

US5913193A Method and system of runtime acoustic unit selection for speech synthesis 失效
标题翻译：用于语音合成的运行时音单元选择的方法和系统
公开(公告)号：US5913193A
公开(公告)日：1999-06-15
申请号：US648808
申请日：1996-04-30
申请人： Xuedong D. Huang , Michael D. Plumpe , Alejandro Acero , James L. Adcock
发明人： Xuedong D. Huang , Michael D. Plumpe , Alejandro Acero , James L. Adcock
IPC分类号： G06F3/16 , G10L13/06 , G10L13/08 , G10L5/02 , G10L9/00
CPC分类号： G10L13/07
摘要： The present invention pertains to a concatenative speech synthesis system and method which produces a more natural sounding speech. The system provides for multiple instances of each acoustic unit which can be used to generate a speech waveform representing an linguistic expression. The multiple instances are formed during an analysis or training phase of the synthesis process and are limited to a robust representation of the highest probability instances. The provision of multiple instances enables the synthesizer to select the instance which closely resembles the desired instance thereby eliminating the need to alter the stored instance to match the desired instance. This in essence minimizes the spectral distortion between the boundaries of adjacent instances thereby producing more natural sounding speech.
摘要翻译：本发明涉及一种产生更自然的声音语音的级联语音合成系统和方法。该系统提供每个声学单元的多个实例，其可用于生成表示语言表达式的语音波形。多个实例在合成过程的分析或训练阶段期间形成，并且被限制为最高概率实例的鲁棒表示。提供多个实例使得合成器能够选择非常类似于期望实例的实例，从而消除了改变存储的实例以匹配所需实例的需要。这实质上使相邻实例的边界之间的频谱失真最小化，从而产生更自然的声音语音。

10. 发明授权

US09111540B2 Local and remote aggregation of feedback data for speech recognition 有权
标题翻译：用于语音识别的反馈数据的本地和远程聚合
公开(公告)号：US09111540B2
公开(公告)日：2015-08-18
申请号：US12481439
申请日：2009-06-09
申请人： Michael D. Plumpe , Julian Odell , Jon Hamaker , Rob Chambers , Christopher Le , Onur Domanic
发明人： Michael D. Plumpe , Julian Odell , Jon Hamaker , Rob Chambers , Christopher Le , Onur Domanic
IPC分类号： G10L15/00 , G10L15/065 , G10L15/30 , G10L15/06
CPC分类号： G10L15/01 , G10L15/02 , G10L15/063 , G10L15/065 , G10L15/14 , G10L15/187 , G10L15/30 , G10L2015/025 , G10L2015/0631 , G10L2015/0635
摘要： A local feedback mechanism for customizing training models based on user data and directed user feedback is provided in speech recognition applications. The feedback data is filtered at different levels to address privacy concerns for local storage and for submittal to a system developer for enhancement of generic training models.
摘要翻译：在语音识别应用中提供了基于用户数据和定向用户反馈定制训练模型的本地反馈机制。反馈数据在不同级别进行过滤，以解决本地存储的隐私问题，并提交给系统开发人员以增强通用培训模型。

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