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

US06216103B1 Method for implementing a speech recognition system to determine speech endpoints during conditions with background noise 失效
标题翻译：用于在具有背景噪声的条件下实现语音识别系统以确定语音端点的方法
公开(公告)号：US06216103B1
公开(公告)日：2001-04-10
申请号：US08957875
申请日：1997-10-20
申请人： Duanpei Wu , Miyuki Tanaka , Ruxin Chen , Lex Olorenshaw
发明人： Duanpei Wu , Miyuki Tanaka , Ruxin Chen , Lex Olorenshaw
IPC分类号： G01L300
CPC分类号： G10L25/87 , G10L15/20
摘要： A method for implementing a speech recognition system for use during conditions with background noise includes the steps of calculating, in real-time, sequential short-term delta energy parameters for speech energy from a spoken utterance, determining threshold values in the speech energy, and identifying a beginning point and an ending point for the spoken utterance based on the relationship between the threshold values and the short-term delta energy parameters.
摘要翻译：用于实现在具有背景噪声的条件期间使用的语音识别系统的方法包括以下步骤：实时地从语音话语中计算语音能量的连续短期增量能量参数，确定语音能量中的阈值，以及基于阈值和短期δ能量参数之间的关系来识别口语发音的起始点和终点。

2. 发明授权

US06718302B1 Method for utilizing validity constraints in a speech endpoint detector 失效
标题翻译：用于在语音端点检测器中使用有效性约束的方法
公开(公告)号：US06718302B1
公开(公告)日：2004-04-06
申请号：US09482396
申请日：2000-01-12
申请人： Duanpei Wu , Miyuki Tanaka , Ruxin Chen , Lex Olorenshaw
发明人： Duanpei Wu , Miyuki Tanaka , Ruxin Chen , Lex Olorenshaw
IPC分类号： G10L1102
CPC分类号： G10L25/87
摘要： A method for utilizing validity constraints in a speech endpoint detector comprises a validity manager that may utilize a pulse width module to validate utterances that include a plurality of energy pulses during a certain time period. The validity manager also may utilize a minimum power module to ensure that speech energy below a pre-determined level is not classified as a valid utterance. In addition the validity manager may use a duration module to ensure that valid utterances fall within a specified duration. Finally, the validity manager may utilize a short-utterance minimum power module to specifically distinguish an utterance of short duration from background noise based on the energy level of the short utterance.
摘要翻译：一种用于在语音端点检测器中利用有限约束的方法包括有效性管理器，其可以利用脉冲宽度模块来在特定时间段期间验证包括多个能量脉冲的话语。有效性管理器还可以利用最小功率模块来确保低于预定电平的语音能量不被分类为有效的话语。此外，有效性管理器可以使用持续时间模块来确保有效的话语落在指定的持续时间内。最后，有效性管理器可以利用短话语最小功率模块来基于短语的能量级别来特别地区分短时间的短时间与背景噪声的发音。

3. 发明授权

US06778959B1 System and method for speech verification using out-of-vocabulary models 失效
标题翻译：使用词汇外模型进行语音验证的系统和方法
公开(公告)号：US06778959B1
公开(公告)日：2004-08-17
申请号：US09691877
申请日：2000-10-18
申请人： Duanpei Wu , Lex Olorenshaw , Xavier Menendez-Pidal , Ruxin Chen
发明人： Duanpei Wu , Lex Olorenshaw , Xavier Menendez-Pidal , Ruxin Chen
IPC分类号： G10L1314
CPC分类号： G10L15/08
摘要： A system and method for speech verification using out-of-vocabulary models includes a speech recognizer that has a model bank with system vocabulary word models, a garbage model, and one or more noise models. The model bank may reject an utterance or other sound as an invalid vocabulary word when the model bank identifies the utterance or other sound as corresponding to the garbage model or the noise models. Initial noise models may be selectively combined into a pre-determined number of final noise model clusters to effectively reduce the number of noise models that are utilized by the model bank of the speech recognizer to verify system vocabulary words.
摘要翻译：使用词汇外模型的语音验证的系统和方法包括语音识别器，其具有具有系统词汇词模型的模型库，垃圾模型和一个或多个噪声模型。当模型库识别与垃圾模型或噪声模型相对应的话语或其他声音时，模型库可以拒绝话语或其他声音作为无效词汇单词。初始噪声模型可以选择性地组合到预定数量的最终噪声模型群集中，以有效地减少由语音识别器的模型库利用以验证系统词汇单词的噪声模型的数量。

4. 发明授权

US06473735B1 System and method for speech verification using a confidence measure 失效
标题翻译：使用置信度测量语音验证的系统和方法
公开(公告)号：US06473735B1
公开(公告)日：2002-10-29
申请号：US09553985
申请日：2000-04-20
申请人： Duanpei Wu , Xavier Menendez-Pidal , Lex Olorenshaw , Ruxin Chen
发明人： Duanpei Wu , Xavier Menendez-Pidal , Lex Olorenshaw , Ruxin Chen
IPC分类号： G10L1506
CPC分类号： G10L15/10 , G10L2015/085
摘要： The present invention comprises a system and method for speech verification using a confidence measure that includes a speech verifier which compares a differential score for a recognized word to a predetermined threshold value, where a recognized word is the word model that produced the highest recognition score. In one embodiment, a single threshold is used for each word in a vocabulary. In another embodiment, each word model has an associated threshold, so that a differential score for a recognized word is compared to a unique threshold associated with that word. In a further embodiment, pairs of confused words in the vocabulary are dealt with separately. If a confused word is the recognized word, the speech verifier compares the differential score to a threshold that depends on the word model that produced the next-highest recognition score. Different values for the various thresholds may maximize rejection accuracy or recognition accuracy. A trade-off between rejection accuracy and recognition accuracy may be made by utilizing an intermediate threshold value that is between a minimum threshold value and a maximum threshold value.
摘要翻译：本发明包括一种用于使用置信度测量的语音验证的系统和方法，所述置信度测量包括将识别的词的差分得分与预定阈值进行比较的语音验证器，其中识别词是产生最高识别分数的单词模型。在一个实施例中，词汇中的每个单词使用单个阈值。在另一个实施例中，每个单词模型具有相关联的阈值，使得将识别的单词的差分分数与与该单词相关联的唯一阈值进行比较。在另一实施例中，词汇表中的混淆词对被单独处理。如果一个混淆的单词是被识别的单词，语音验证器将差分分数与取决于产生下一最高识别分数的单词模型的阈值进行比较。各种阈值的不同值可以最大化拒绝准确度或识别精度。可以通过利用处于最小阈值和最大阈值之间的中间阈值来进行拒绝准确度和识别精度之间的折衷。

5. 发明授权

US06173258B2 Method for reducing noise distortions in a speech recognition system 失效
标题翻译：降低语音识别系统噪声失真的方法
公开(公告)号：US06173258B2
公开(公告)日：2001-01-09
申请号：US09177461
申请日：1998-10-22
申请人： Xavier Menendez-Pidal , Miyuki Tanaka , Ruxin Chen , Duanpei Wu
发明人： Xavier Menendez-Pidal , Miyuki Tanaka , Ruxin Chen , Duanpei Wu
IPC分类号： G10L506
CPC分类号： G10L21/0208 , G10L15/02 , G10L21/0264
摘要： A method for reducing noise distortions in a speech recognition system comprises a feature extractor that includes a noise-suppressor, one or more time cosine transforms, and a normalizer. The noise-suppressor preferably performs a spectral subtraction process early in the feature extraction procedure. The time cosine transforms preferably operate in a centered-mode to each perform a transformation in the time domain. The normalizer calculates and utilizes normalization values to generate normalized features for speech recognition. The calculated normalization values preferably include mean values, left variances and right variances.
摘要翻译：一种用于减少语音识别系统中的噪声失真的方法包括：特征提取器，其包括噪声抑制器，一个或多个时间余弦变换和归一化器。噪声抑制器优选地在特征提取过程的早期执行频谱减法处理。时间余弦变换优选地以居中模式操作，以在时域中执行变换。归一化器计算并利用归一化值来生成用于语音识别的归一化特征。计算的归一化值优选包括平均值，左方差和右方差。

6. 发明授权

US6006186A Method and apparatus for a parameter sharing speech recognition system 失效
标题翻译：一种参数共享语音识别系统的方法和装置
公开(公告)号：US6006186A
公开(公告)日：1999-12-21
申请号：US953026
申请日：1997-10-16
申请人： Ruxin Chen , Miyuki Tanaka , Duanpei Wu , Lex S. Olorenshaw
发明人： Ruxin Chen , Miyuki Tanaka , Duanpei Wu , Lex S. Olorenshaw
IPC分类号： G10L15/14 , G10L15/18 , G10L7/08
CPC分类号： G10L15/142 , G10L15/148
摘要： A method and an apparatus for a parameter sharing speech recognition system are provided. Speech signals are received into a processor of a speech recognition system. The speech signals are processed using a speech recognition system hosting a shared hidden Markov model (HMM) produced by generating a number of phoneme models, some of which are shared. The phoneme models are generated by retaining as a separate phoneme model any triphone model having a number of trained frames available that exceeds a prespecified threshold. A shared phoneme model is generated to represent each of the groups of triphone phoneme models for which the number of trained frames having a common biphone exceed the prespecified threshold. A shared phoneme model is generated to represent each of the groups of triphone phoneme models for which the number of trained frames having an equivalent effect on a phonemic context exceed the prespecified threshold. A shared phoneme model is generated to represent each of the groups of triphone phoneme models having the same center context. The generated phoneme models are trained, and shared phoneme model states are generated that are shared among the phoneme models. Shared probability distribution functions are generated that are shared among the phoneme model states. Shared probability sub-distribution functions are generated that are shared among the phoneme model probability distribution functions. The shared phoneme model hierarchy is reevaluated for further sharing in response to the shared probability sub-distribution functions. Signals representative of the received speech signals are generated.
摘要翻译：提供了一种用于参数共享语音识别系统的方法和装置。语音信号被接收到语音识别系统的处理器中。语音信号使用一个语音识别系统进行处理，该语音识别系统承载通过生成许多音素模型而产生的共享隐马尔可夫模型（HMM），其中一些是共享的。音素模型是通过保留作为单独音素模型的任何具有超过预定阈值的已训练帧数的三音模型而产生的。生成共享音素模型以表示具有共同biphone的经过训练的帧的数量超过预定阈值的三音节音素模型组中的每一组。生成共享音素模型以表示三音节音素模型中的每一组，其中对音素上下文具有等效影响的经过训练的帧的数量超过预先指定的阈值。生成共享音素模型以表示具有相同中心上下文的三音节音素模型组中的每一组。生成的音素模型被训练，并且生成在音素模型中共享的共享音素模型状态。生成在音素模型状态之间共享的共享概率分布函数。生成在音素模型概率分布函数中共享的共享概率子分布函数。共享音素模型层次结构被重新评估以响应于共享概率子分布函数进一步共享。生成表示接收到的语音信号的信号。

7. 发明授权

US06768979B1 Apparatus and method for noise attenuation in a speech recognition system 失效
标题翻译：语音识别系统中噪声衰减的装置和方法
公开(公告)号：US06768979B1
公开(公告)日：2004-07-27
申请号：US09282809
申请日：1999-03-31
申请人： Xavier Menéndez-Pidal , Miyuki Tanaka , Ruxin Chen
发明人： Xavier Menéndez-Pidal , Miyuki Tanaka , Ruxin Chen
IPC分类号： G10L2102
CPC分类号： G10L21/0208 , F16J15/43 , G10L15/02 , G10L21/0264 , G11B19/2009
摘要： The noise suppressor utilizes statistical characteristics of the noise signal to attenuate amplitude values of the noisy speech signal that have a probability of containing noise. In one embodiment, the noise suppressor utilizes an attenuation function having a shape determined in part by a noise average and a noise standard deviation. In a further embodiment, the noise suppressor also utilizes an adaptive attenuation coefficient that depends on signal-to-noise conditions in the speech recognition system.
摘要翻译：噪声抑制器利用噪声信号的统计特性来衰减具有包含噪声的概率的噪声语音信号的振幅值。在一个实施例中，噪声抑制器利用具有部分由噪声平均值和噪声标准偏差确定的形状的衰减函数。在另一实施例中，噪声抑制器还利用取决于语音识别系统中的信噪比条件的自适应衰减系数。

8. 发明授权

US08880395B2 Source separation by independent component analysis in conjunction with source direction information 有权
标题翻译：源分离与独立成分分析结合源方向信息
公开(公告)号：US08880395B2
公开(公告)日：2014-11-04
申请号：US13464828
申请日：2012-05-04
申请人： Jaekwon Yoo , Ruxin Chen
发明人： Jaekwon Yoo , Ruxin Chen
IPC分类号： G10L21/00
CPC分类号： G10L21/0272
摘要： Methods and apparatus for signal processing are disclosed. Source separation can be performed to extract source signals from mixtures of source signals by way of independent component analysis. Source direction information is utilized in the separation process, and independent component analysis techniques described herein use multivariate probability density functions to preserve the alignment of frequency bins in the source separation process. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.
摘要翻译：公开了用于信号处理的方法和装置。可以通过独立分量分析来执行源分离以从源信号的混合中提取源信号。在分离过程中使用源方向信息，并且本文描述的独立分量分析技术使用多变量概率密度函数来保持源分离过程中频率仓的对准。要强调的是，该摘要被提供以符合要求抽象的规则，允许搜索者或其他读者快速确定技术公开内容的主题。提交它的理解是，它不会用于解释或限制权利要求的范围或含义。

9. 发明申请

US20140237277A1 HYBRID PERFORMANCE SCALING OR SPEECH RECOGNITION 有权
标题翻译：混合性能缩放或语音识别
公开(公告)号：US20140237277A1
公开(公告)日：2014-08-21
申请号：US13791716
申请日：2013-03-08
申请人： Dominic S. Mallinson , Ruxin Chen
发明人： Dominic S. Mallinson , Ruxin Chen
IPC分类号： G06F1/32
CPC分类号： G06F1/3206 , G06F1/3203 , G06F1/3231 , G06F1/3293 , G06F3/017 , G10L15/22 , G10L25/78 , Y02D10/122 , Y02D10/173
摘要： Aspects of the present disclosure describe methods and apparatuses for executing operations on a client device platform that is operating in a low-power state. A first analysis may be used to assign a first confidence score to a recorded non-tactile input. When the first confidence score is above a first threshold an intermediate-power state may be activated. A second more detailed analysis may then assign a second confidence score to the non-tactile input. When the second confidence score is above a second threshold, then the operation is initiated. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.
摘要翻译：本公开的方面描述了在以低功率状态运行的客户端设备平台上执行操作的方法和装置。可以使用第一分析来将第一置信度分数分配给记录的非触觉输入。当第一置信度高于第一阈值时，可以激活中间功率状态。然后，第二更详细的分析可以向非触觉输入分配第二置信度分数。当第二置信度分数高于第二阈值时，开始该操作。要强调的是，该摘要被提供以符合要求抽象的规则，允许搜索者或其他读者快速确定技术公开内容的主题。提交它的理解是，它不会用于解释或限制权利要求的范围或含义。

10. 发明授权

US08756061B2 Speech syllable/vowel/phone boundary detection using auditory attention cues 有权
标题翻译：语音音节/元音/电话边界检测使用听觉注意线索
公开(公告)号：US08756061B2
公开(公告)日：2014-06-17
申请号：US13078866
申请日：2011-04-01
申请人： Ozlem Kalinli , Ruxin Chen
发明人： Ozlem Kalinli , Ruxin Chen
IPC分类号： G10L15/04
CPC分类号： G10L15/05 , G10L15/04 , G10L15/16 , G10L15/24 , G10L15/34 , G10L25/03
摘要： In syllable or vowel or phone boundary detection during speech, an auditory spectrum may be determined for an input window of sound and one or more multi-scale features may be extracted from the auditory spectrum. Each multi-scale feature can be extracted using a separate two-dimensional spectro-temporal receptive filter. One or more feature maps corresponding to the one or more multi-scale features can be generated and an auditory gist vector can be extracted from each of the one or more feature maps. A cumulative gist vector may be obtained through augmentation of each auditory gist vector extracted from the one or more feature maps. One or more syllable or vowel or phone boundaries in the input window of sound can be detected by mapping the cumulative gist vector to one or more syllable or vowel or phone boundary characteristics using a machine learning algorithm.
摘要翻译：在语音期间的音节或元音或电话边界检测中，可以为输入声音窗口确定听觉频谱，并且可以从听觉谱中提取一个或多个多尺度特征。可以使用单独的二维光谱接收滤波器来提取每个多尺度特征。可以生成与一个或多个多尺度特征相对应的一个或多个特征图，并且可以从一个或多个特征图中的每一个提取听觉要点矢量。可以通过增加从一个或多个特征图提取的每个听觉要素矢量来获得累积的要点向量。通过使用机器学习算法将累积的要点向量映射到一个或多个音节或元音或电话边界特征，可以检测声音的输入窗口中的一个或多个音节或元音或电话边界。

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