公开(公告)号：US20100223060A1

公开(公告)日：2010-09-02

申请号：US12541872

申请日：2009-08-14

申请人： Yao-Yuan Chang ,  Sen-Chia Chang ,  Shih-Chieh Chien ,  Jia-Jang Tu

发明人： Yao-Yuan Chang ,  Sen-Chia Chang ,  Shih-Chieh Chien ,  Jia-Jang Tu

IPC分类号： G10L11/00 ,  G10L21/00

CPC分类号： G10L15/22 ,  G10L2015/228

摘要： The present invention relates to a speech interactive system and method. The system comprises a target information receiving module, an interactive mode setting and speech processing module, an interactive information update module, a decision module, and an output response module. It receives target information and sets corresponding target text sentence information. It also receives a user's speech signal, sets an interactive mode, decides the speech's target text sentence information, and generates an assessment for the target text sentence. Under the set interactive mode, the system updates the information in an interactive information recording table according to the assessment and a timing count. According to the interactive mode and the recorded information, an output mode for the target text sentence information is generated. According to the output mode and the recorded information, the response information is generated.

摘要翻译： 本发明涉及语音交互系统和方法。 该系统包括目标信息接收模块，交互模式设置和语音处理模块，交互式信息更新模块，决策模块和输出响应模块。 它接收目标信息并设置相应的目标文字信息。 它还接收用户的语音信号，设置交互模式，决定语音的目标文字信息，并产生目标文本句子的评估。 在设置的交互模式下，系统根据评估和定时计数更新交互式信息记录表中的信息。 根据交互模式和记录信息，生成目标文字信息的输出模式。 根据输出模式和记录信息，产生响应信息。

公开(公告)号：US08234114B2

公开(公告)日：2012-07-31

申请号：US12541872

申请日：2009-08-14

申请人： Yao-Yuan Chang ,  Sen-Chia Chang ,  Shih-Chieh Chien ,  Jia-Jang Tu

发明人： Yao-Yuan Chang ,  Sen-Chia Chang ,  Shih-Chieh Chien ,  Jia-Jang Tu

IPC分类号： G10L15/04

CPC分类号： G10L15/22 ,  G10L2015/228

摘要： The present invention relates to a speech interactive system and method. The system comprises a target information receiving module, an interactive mode setting and speech processing module, an interactive information update module, a decision module, and an output response module. It receives target information and sets corresponding target text sentence information. It also receives a user's speech signal, sets an interactive mode, decides the speech's target text sentence information, and generates an assessment for the target text sentence. Under the set interactive mode, the system updates the information in an interactive information recording table according to the assessment and a timing count. According to the interactive mode and the recorded information, an output mode for the target text sentence information is generated. According to the output mode and the recorded information, the response information is generated.

摘要翻译： 本发明涉及语音交互系统和方法。 该系统包括目标信息接收模块，交互模式设置和语音处理模块，交互式信息更新模块，决策模块和输出响应模块。 它接收目标信息并设置相应的目标文字信息。 它还接收用户的语音信号，设置交互模式，决定语音的目标文字信息，并产生目标文本句子的评估。 在设置的交互模式下，系统根据评估和定时计数更新交互式信息记录表中的信息。 根据交互模式和记录信息，生成目标文字信息的输出模式。 根据输出模式和记录信息，产生响应信息。

公开(公告)号：US07043429B2

公开(公告)日：2006-05-09

申请号：US10107314

申请日：2002-03-28

申请人： Sen-Chia Chang ,  Shih-Chien Chien ,  Jia-Jang Tu

发明人： Sen-Chia Chang ,  Shih-Chien Chien ,  Jia-Jang Tu

IPC分类号： G10L15/08

CPC分类号： G10L15/32 ,  G10L15/08

摘要： A speech recognition system is used to receive a speech signal and output an output language word with respect to the speech signal. The speech recognition system has preset quantities for a first threshold, a second threshold, and a third threshold. The speech recognition system includes a first speech recognition device that is used to receive the speech signal and generate a first candidate language word and a first confidence measurement of the first candidate language word, according to the speech signal. A second speech recognition device is used to receive the speech signal and generate a second candidate language word and a second confidence measurement of the second candidate language word, according to the speech signal. A confidence measurement judging unit is used to output the language word, by comparing the first confidence measurement and the second confidence measurement to the above thresholds.

摘要翻译： 语音识别系统用于接收语音信号并输出​​相对于语音信号的输出语言字。 语音识别系统具有第一阈值，第二阈值和第三阈值的预设量。 语音识别系统包括：第一语音识别装置，用于接收语音信号，并根据语音信号产生第一候选语言字和第一候选语言字的第一置信度测量值。 根据语音信号，第二语音识别装置用于接收语音信号并产生第二候选语言字和第二候选语言字的第二置信度测量。 通过将第一置信度测量和第二置信度测量值与上述阈值进行比较，使用置信度测量判断单元来输出语言单词。

公开(公告)号：US07617101B2

公开(公告)日：2009-11-10

申请号：US10628361

申请日：2003-07-29

申请人： Sen-Chia Chang ,  Shih-Chieh Chien

发明人： Sen-Chia Chang ,  Shih-Chieh Chien

IPC分类号： G10L15/16

CPC分类号： G10L15/08 ,  G10L15/16

摘要： A method and system for utterance verification is disclosed. It first extracts a sequence of feature vectors from speech signal. At least one candidate string is obtained after speech recognition. Then, speech signal is segmented into speech segments according to the verification-unit-specified structure of candidate string for making each speech segment corresponding to a verification unit. After calculating the verification feature vectors of speech segments, these verification feature vectors are sequentially used to generate verification scores of speech segments in verification process. This invention uses neural networks for calculating verification scores, where each neural network is a Multi-Layer Perceptron (MLP) developed for each verification unit. Verification score is obtained through using feed-forward process of MLP. Finally, utterance verification score is obtained by combining all verification scores of speech segments and is used to compare with a pre-defined threshold for the decision of acceptance or rejection of the candidate string.

摘要翻译： 公开了一种用于话语验证的方法和系统。 它首先从语音信号中提取特征向量序列。 在语音识别之后至少有一个候选字符串被获得。 然后，根据用于使每个对应于验证单元的语音段的候选串的验证单元指定的结构将语音信号分段成语音段。 在计算语音段的验证特征向量之后，这些验证特征向量被顺序地用于在验证过程中产生语音段的验证分数。 本发明使用神经网络来计算验证分数，其中每个神经网络是为每个验证单元开发的多层感知器（MLP）。 通过使用MLP的前馈过程获得验证分数。 最后，通过组合语音段的所有验证分数获得话语验证分数，并且用于与候选字符串的接受或拒绝的决定的预定义阈值进行比较。

公开(公告)号：US06567776B1

公开(公告)日：2003-05-20

申请号：US09542844

申请日：2000-04-04

申请人： Sen-Chia Chang ,  Shih-Chieh Chien ,  Chung-Mou Penwu

发明人： Sen-Chia Chang ,  Shih-Chieh Chien ,  Chung-Mou Penwu

IPC分类号： G10L1506

CPC分类号： G10L15/063 ,  G10L2015/0631

摘要： In speaker-independent speech recognition, between-speaker variability is one of the major resources of recognition errors. A speaker cluster model is used to manage recognition problems caused by between-speaker variability. In the training phase, the score function is used as a discriminative function. The parameters of at least two cluster-dependent models are adjusted through a discriminative training method to improve performance of the speech recognition.

摘要翻译： 在与扬声器无关的语音识别中，扬声器之间的变异性是识别错误的主要资源之一。 扬声器群集模型用于管理扬声器间变异性引起的识别问题。 在训练阶段，分数函数被用作辨别函数。 通过歧视性训练方法调整至少两个群集相关模型的参数，以提高语音识别的性能。

公开(公告)号：US06760702B2

公开(公告)日：2004-07-06

申请号：US09907678

申请日：2001-07-19

申请人： Shih-Chieh Chien ,  Sen-Chia Chang

发明人： Shih-Chieh Chien ,  Sen-Chia Chang

IPC分类号： G10L1504

CPC分类号： G10L15/083

摘要： A method for generating candidate word strings in speech recognition is provided, which is based on the nodes in the word lattice to search candidate word strings. The associated maximum string score for each node is first determined. Next, all nodes are sorted based on the associated maximum string score to group the nodes with the same string score into the same node set. Then, the node sets with relative high string scores are selected to connect the nodes by their starting time frame and ending time frame, thereby generating the candidate word strings.

摘要翻译： 提供了一种用于在语音识别中生成候选词串的方法，其基于词格中的节点来搜索候选词串。 首先确定每个节点的相关联的最大字符串得分。 接下来，根据相关联的最大字符串分数对所有节点进行排序，将具有相同字符串分数的节点分组到同一个节点集中。 然后，选择具有相对较高字符串分数的节点，以便通过其开始时间帧和结束时间帧连接节点，从而生成候选字串。

公开(公告)号：US06456697B1

公开(公告)日：2002-09-24

申请号：US09394191

申请日：1999-09-10

申请人： Sen-Chia Chang ,  Shih-Chieh Chien

发明人： Sen-Chia Chang ,  Shih-Chieh Chien

IPC分类号： H04M164

CPC分类号： G10L15/20 ,  G10L15/10 ,  G10L25/30 ,  H04M1/64 ,  H04M2201/40

摘要： Device and method of channel effect compensation for a telephone speech recognition system is disclosed. The telephone speech recognition system comprises a compensatory neutral network and a recognize. The compensatory neural network receives an input signal and compensates the input signal with a bias to generate an output signal. The compensatory neural network provides a plurality of first parameters to determine the bias. The recognizer is coupled to the compensatory neural network for classifying the output signal according to a plurality of second parameters in acoustic models to generate a recognition result and determine a recognition loss. The first parameters and second parameters are adjusted according to the recognition loss and an adjustment means during a training process.

摘要翻译： 公开了一种用于电话语音识别系统的信道效应补偿的装置和方法。 电话语音识别系统包括补偿中性网络和识别。 补偿神经网络接收输入信号并用偏置补偿输入信号以产生输出信号。 补偿神经网络提供多个第一参数来确定偏差。 识别器耦合到补偿神经网络，用于根据声学模型中的多个第二参数对输出信号进行分类，以产生识别结果并确定识别损失。 第一参数和第二参数根据识别损失和训练过程中的调整手段进行调整。

公开(公告)号：US20120034581A1

公开(公告)日：2012-02-09

申请号：US12900482

申请日：2010-10-08

申请人： Sen-Chia Chang ,  Hsien-Cheng Liao ,  Jiang-Chun Chen

发明人： Sen-Chia Chang ,  Hsien-Cheng Liao ,  Jiang-Chun Chen

IPC分类号： G09B19/06

CPC分类号： G09B19/06

摘要： A language learning system including a storage module, a feature extraction module, and an assessment and diagnosis module is provided. The storage module stores training data and an assessment decision tree generated according to the training data. The feature extraction module extracts pronunciation features of a pronunciation given by a language learner. The assessment and diagnosis module identifies a diagnosis path corresponding to the pronunciation of the language learner in the assessment decision tree and outputs feedback information corresponding to the diagnosis path. Thereby, the language learning system can assess and provide feedback information regarding words, phrases or sentences pronounced by the language learner.

摘要翻译： 提供了包括存储模块，特征提取模块和评估和诊断模块的语言学习系统。 存储模块存储根据训练数据生成的训练数据和评估决策树。 特征提取模块提取由语言学习者给出的发音的发音特征。 评估和诊断模块识别与评估决策树中的语言学习者的发音相对应的诊断路径，并输出与诊断路径相对应的反馈信息。 因此，语言学习系统可以评估和提供关于语言学习者发音的单词，短语或句子的反馈信息。

公开(公告)号：US20110161084A1

公开(公告)日：2011-06-30

申请号：US12822188

申请日：2010-06-24

申请人： Cheng-Hsien Lin ,  Sen-Chia Chang ,  Chi-Tien Chiu

发明人： Cheng-Hsien Lin ,  Sen-Chia Chang ,  Chi-Tien Chiu

IPC分类号： G10L15/00

CPC分类号： G10L15/08

摘要： Apparatus, method and system for generating a threshold for utterance verification are introduced herein. When a processing object is determined, a recommendation threshold is generated according to an expected utterance verification result. In addition, extra collection of corpuses or training models is not necessary for the utterance verification introduced here. The processing unit can be a recognition object or an utterance verification object. In the apparatus, method and system for generating a threshold for utterance verification, at least one of the processing objects is received and then a speech unit sequence is generated therefrom. One or more values corresponding to each of the speech unit of the speech unit sequence are obtained accordingly, and then a recommendation threshold is generated based on an expected utterance verification result.

摘要翻译： 本文介绍了用于产生语音验证阈值的装置，方法和系统。 当确定处理对象时，根据预期的话语验证结果生成推荐阈值。 此外，这里介绍的语音验证不需要额外收集语料库或培训模型。 处理单元可以是识别对象或话语验证对象。 在用于产生用于话语验证的阈值的装置，方法和系统中，接收至少一个处理对象，然后从其生成语音单元序列。 相应地获得与语音单元序列的每个语音单元相对应的一个或多个值，然后基于预期的话语验证结果生成推荐阈值。

公开(公告)号：US20070078652A1

公开(公告)日：2007-04-05

申请号：US11372923

申请日：2006-03-11

申请人： Sen-Chia Chang ,  Yuan-Fu Liao ,  Jeng-Shien Lin

发明人： Sen-Chia Chang ,  Yuan-Fu Liao ,  Jeng-Shien Lin

IPC分类号： G10L21/02

CPC分类号： G10L15/00 ,  G10L21/02

摘要： A system and method for detecting the recognizability of input speech signal is provided. It is designed in the pre-stage of speech recognition or a dialog system. The invention detects the user's environmental condition and verifies if the input speech signal can be recognized. It mainly comprises an environment parameter generator, a signal recognition verifier, and a strategy response processor. Through the use of the invention in the pre-stage of speech recognition or a dialog system, it can precisely verify the recognizability of the input speech signal and receives the input speech signals of high recognition probability in a noisy environment. This reduces the impact caused by the receiving the input speech signals of low recognition probability. This invention thus increases the recognition probability for a recognizer.

摘要翻译： 提供了一种用于检测输入语音信号的可识别性的系统和方法。 它是在语音识别或对话系统的前期设计的。 本发明检测用户的环境状况并验证输入语音信号是否可被识别。 它主要包括环境参数发生器，信号识别验证器和策略响应处理器。 通过在语音识别或对话系统的前期使用本发明，可以精确地验证输入语音信号的可识别性，并且在嘈杂的环境中接收具有高识别概率的输入语音信号。 这减少了由接收低识别概率的输入语音信号引起的影响。 因此，本发明增加了识别器的识别概率。