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

US09299345B1 Bootstrapping language models for spoken dialog systems using the world wide web 有权
标题翻译：使用万维网的口语对话系统的自举语言模型
公开(公告)号：US09299345B1
公开(公告)日：2016-03-29
申请号：US11425243
申请日：2006-06-20
申请人： Mazin Gilbert , Dilek Z. Hakkani-Tur
发明人： Mazin Gilbert , Dilek Z. Hakkani-Tur
IPC分类号： G10L15/00 , G10L15/14 , G10L15/22 , G10L15/30
CPC分类号： G10L15/22 , G06F17/279 , G10L15/183 , G10L15/30
摘要： A system, method and computer readable medium that generates a language model from data from a web domain is disclosed. The method may include filtering web data to remove unwanted data from the web domain data, extracting predicate/argument pairs from the filtered web data, generating conversational utterances by merging the extracted predicate/argument pairs into conversational templates, and generating a web data language model using the generated conversational utterances.
摘要翻译：公开了一种从Web域的数据生成语言模型的系统，方法和计算机可读介质。该方法可以包括过滤web数据以从Web域数据中移除不需要的数据，从过滤的web数据中提取谓词/参数对，通过将提取的谓词/参数对合并成对话模板来生成对话话语，以及生成Web数据语言模型使用生成的会话话语。

2. 发明授权

US08650033B1 Method of active learning for automatic speech recognition 有权
标题翻译：自动语音识别主动学习方法
公开(公告)号：US08650033B1
公开(公告)日：2014-02-11
申请号：US11549395
申请日：2006-10-13
申请人： Allen Louis Gorin , Dilek Z. Hakkani-Tur , Giuseppe Riccardi
发明人： Allen Louis Gorin , Dilek Z. Hakkani-Tur , Giuseppe Riccardi
IPC分类号： G10L15/06
CPC分类号： G10L15/063
摘要： State-of-the-art speech recognition systems are trained using transcribed utterances, preparation of which is labor-intensive and time-consuming. The present invention is an iterative method for reducing the transcription effort for training in automatic speech recognition (ASR). Active learning aims at reducing the number of training examples to be labeled by automatically processing the unlabeled examples and then selecting the most informative ones with respect to a given cost function for a human to label. The method comprises automatically estimating a confidence score for each word of the utterance and exploiting the lattice output of a speech recognizer, which was trained on a small set of transcribed data. An utterance confidence score is computed based on these word confidence scores; then the utterances are selectively sampled to be transcribed using the utterance confidence scores.
摘要翻译：最先进的语音识别系统是使用转录语言进行训练，其准备是劳动密集型和耗时的。本发明是用于减少自动语音识别（ASR）中训练的转录努力的迭代方法。主动学习旨在通过自动处理未标记的示例，然后针对人类给定的成本函数选择最具信息的示例来减少要标注的训练示例的数量。该方法包括自动估计每个词语的置信度，并利用在一小组转录数据上训练的语音识别器的格子输出。基于这些单词置信度得出一个话语置信度得分; 然后使用话语置信度得分选择性地采样语音以进行转录。

3. 发明授权

US08204749B2 System and method for building emotional machines 有权
标题翻译：情感机器的系统和方法
公开(公告)号：US08204749B2
公开(公告)日：2012-06-19
申请号：US13053179
申请日：2011-03-21
申请人： Dilek Z. Hakkani-Tur , Jackson J. Liscombe , Guiseppe Riccardi
发明人： Dilek Z. Hakkani-Tur , Jackson J. Liscombe , Guiseppe Riccardi
IPC分类号： G10L21/00 , G06F17/20 , G06F17/27 , G10L15/00 , G10L15/18
CPC分类号： G06F17/274 , G10L15/1807 , G10L17/26
摘要： A system, method and computer-readable medium for practicing a method of emotion detection during a natural language dialog between a human and a computing device are disclosed. The method includes receiving an utterance from a user in a natural language dialog, receiving contextual information regarding the natural language dialog which is related to changes of emotion over time in the dialog, and detecting an emotion of the user based on the received contextual information. Examples of contextual information include, for example, differential statistics, joint statistics and distance statistics.
摘要翻译：公开了一种用于在人与计算设备之间的自然语言对话中练习情感检测方法的系统，方法和计算机可读介质。该方法包括在自然语言对话中从用户接收话语，在对话中接收与随时间推移的情绪变化相关的自然语言对话的上下文信息，以及基于接收到的上下文信息来检测用户的情绪。情境信息的例子包括例如差异统计，联合统计和距离统计。

4. 发明授权

US08185399B2 System and method of providing an automated data-collection in spoken dialog systems 有权
标题翻译：在口头对话系统中提供自动数据收集的系统和方法
公开(公告)号：US08185399B2
公开(公告)日：2012-05-22
申请号：US11029798
申请日：2005-01-05
申请人： Giuseppe Di Fabbrizio , Dilek Z. Hakkani-Tur , Mazin G. Rahim , Bernard S. Renger , Gokhan Tur
发明人： Giuseppe Di Fabbrizio , Dilek Z. Hakkani-Tur , Mazin G. Rahim , Bernard S. Renger , Gokhan Tur
IPC分类号： G10L21/00 , G10L19/00 , G06F17/27
CPC分类号： G10L15/063 , G10L15/183 , G10L15/22
摘要： The invention relates to a system and method for gathering data for use in a spoken dialog system. An aspect of the invention is generally referred to as an automated hidden human that performs data collection automatically at the beginning of a conversation with a user in a spoken dialog system. The method comprises presenting an initial prompt to a user, recognizing a received user utterance using an automatic speech recognition engine and classifying the recognized user utterance using a spoken language understanding module. If the recognized user utterance is not understood or classifiable to a predetermined acceptance threshold, then the method re-prompts the user. If the recognized user utterance is not classifiable to a predetermined rejection threshold, then the method transfers the user to a human as this may imply a task-specific utterance. The received and classified user utterance is then used for training the spoken dialog system.
摘要翻译：本发明涉及一种用于收集在口头对话系统中使用的数据的系统和方法。本发明的一个方面通常被称为在与对话系统中的用户的对话开始时自动执行数据收集的自动隐藏人。该方法包括向用户呈现初始提示，使用自动语音识别引擎识别接收到的用户话语，并使用口语理解模块对所识别的用户话语进行分类。如果识别的用户话语不能被理解或可被分类到预定的接受阈值，则该方法重新提示用户。如果识别的用户话语不能被分类为预定的拒绝阈值，则该方法将用户转移给人，因为这可能意味着任务特定的话语。然后，接收和分类的用户话语用于训练口语对话系统。

5. 发明授权

US07949525B2 Active labeling for spoken language understanding 有权
标题翻译：积极标注口语理解
公开(公告)号：US07949525B2
公开(公告)日：2011-05-24
申请号：US12485103
申请日：2009-06-16
申请人： Dilek Z. Hakkani-Tur , Mazin G. Rahim , Gokhan Tur
发明人： Dilek Z. Hakkani-Tur , Mazin G. Rahim , Gokhan Tur
IPC分类号： G10L15/00 , G10L15/06 , G10L15/20
CPC分类号： G10L15/1822
摘要： A spoken language understanding method and system are provided. The method includes classifying a set of labeled candidate utterances based on a previously trained classifier, generating classification types for each candidate utterance, receiving confidence scores for the classification types from the trained classifier, sorting the classified utterances based on an analysis of the confidence score of each candidate utterance compared to a respective label of the candidate utterance, and rechecking candidate utterances according to the analysis. The system includes modules configured to control a processor in the system to perform the steps of the method.
摘要翻译：提供口语理解方法和系统。该方法包括基于先前训练的分类器对一组标记的候选话语进行分类，为每个候选语音生成分类类型，从训练分类器接收分类类型的置信度分数，每个候选话语与候选话语的相应标签相比较，并且根据分析重新检查候选话语。该系统包括被配置为控制系统中的处理器以执行该方法的步骤的模块。

6. 发明授权

US07742911B2 Apparatus and method for spoken language understanding by using semantic role labeling 有权
标题翻译：通过使用语义角色标注来进行口语理解的装置和方法
公开(公告)号：US07742911B2
公开(公告)日：2010-06-22
申请号：US11095299
申请日：2005-03-31
申请人： Ananlada Chotimongkol , Dilek Z. Hakkani-Tur , Gokhan Tur
发明人： Ananlada Chotimongkol , Dilek Z. Hakkani-Tur , Gokhan Tur
IPC分类号： G06F17/28
CPC分类号： G06F17/278 , G06F17/2785 , G10L15/1822 , G10L15/22
摘要： An apparatus and a method are provided for using semantic role labeling for spoken language understanding. A received utterance semantically parsed by semantic role labeling. A predicate or at least one argument is extracted from the semantically parsed utterance. An intent is estimated based on the predicate or the at least one argument. In another aspect, a method is provided for training a spoken language dialog system that uses semantic role labeling. An expert is provided with a group of predicate/argument pairs. Ones of the predicate/argument pairs are selected as intents. Ones of the arguments are selected as named entities. Mappings from the arguments to frame slots are designed.
摘要翻译：提供了一种使用语义角色标识来进行语言理解的装置和方法。被语义角色标注语义解析的语音接收语句。从语义解析的话语中提取谓词或至少一个参数。根据谓词或至少一个参数估计意图。另一方面，提供了一种用于训练使用语义角色标注的口语对话系统的方法。专家提供了一组谓词/参数对。谓词/参数对的一部分被选为意图。参数的一部分被选为命名实体。从框架插槽的参数映射被设计。

7. 发明授权

US07571098B1 System and method of spoken language understanding using word confusion networks 有权
标题翻译：使用词混淆网络的口语理解的系统和方法
公开(公告)号：US07571098B1
公开(公告)日：2009-08-04
申请号：US10448149
申请日：2003-05-29
申请人： Allen Louis Gorin , Dilek Z. Hakkani-Tur , Giuseppe Riccardi , Gokhan Tur , Jeremy Huntley Wright
发明人： Allen Louis Gorin , Dilek Z. Hakkani-Tur , Giuseppe Riccardi , Gokhan Tur , Jeremy Huntley Wright
IPC分类号： G10L15/18 , G10L15/00 , G10L15/06 , G10L15/28 , G06F17/27
CPC分类号： G10L15/1822 , G06F17/2775 , G10L15/08
摘要： Word lattices that are generated by an automatic speech recognition system are used to generate a modified word lattice that is usable by a spoken language understanding module. In one embodiment, the spoken language understanding module determines a set of salient phrases by calculating an intersection of the modified word lattice, which is optionally preprocessed, and a finite state machine that includes a plurality of salient grammar fragments.
摘要翻译：由自动语音识别系统生成的词格子用于生成可由口头语言理解模块使用的修改词格。在一个实施例中，口语理解模块通过计算可选地预处理的修改字格点和包括多个显着语法片段的有限状态机的交集来确定一组显着短语。

8. 发明申请

US20120232898A1 SYSTEM AND METHOD OF PROVIDING AN AUTOMATED DATA-COLLECTION IN SPOKEN DIALOG SYSTEMS 有权
标题翻译：系统和方法提供自动数据收集在风扇对话系统
公开(公告)号：US20120232898A1
公开(公告)日：2012-09-13
申请号：US13476150
申请日：2012-05-21
申请人： Giuseppe Di Fabbrizio , Dilek Z. Hakkani-Tur , Mazin G. Rahim , Bernard S. Renger , Gokhan Tur
发明人： Giuseppe Di Fabbrizio , Dilek Z. Hakkani-Tur , Mazin G. Rahim , Bernard S. Renger , Gokhan Tur
IPC分类号： G10L15/26 , G10L15/04
CPC分类号： G10L15/063 , G10L15/183 , G10L15/22
摘要： The invention relates to a system and method for gathering data for use in a spoken dialog system. An aspect of the invention is generally referred to as an automated hidden human that performs data collection automatically at the beginning of a conversation with a user in a spoken dialog system. The method comprises presenting an initial prompt to a user, recognizing a received user utterance using an automatic speech recognition engine and classifying the recognized user utterance using a spoken language understanding module. If the recognized user utterance is not understood or classifiable to a predetermined acceptance threshold, then the method re-prompts the user. If the recognized user utterance is not classifiable to a predetermined rejection threshold, then the method transfers the user to a human as this may imply a task-specific utterance. The received and classified user utterance is then used for training the spoken dialog system.
摘要翻译：本发明涉及一种用于收集在口头对话系统中使用的数据的系统和方法。本发明的一个方面通常被称为在与对话系统中的用户的对话开始时自动执行数据收集的自动隐藏人。该方法包括向用户呈现初始提示，使用自动语音识别引擎识别接收到的用户话语，并使用口语理解模块对所识别的用户话语进行分类。如果识别的用户话语不能被理解或可被分类到预定的接受阈值，则该方法重新提示用户。如果识别的用户话语不能被分类为预定的拒绝阈值，则该方法将用户转移给人，因为这可能意味着任务特定的话语。然后，接收和分类的用户话语用于训练口语对话系统。

9. 发明申请

US20110172999A1 System and Method for Building Emotional Machines 有权
标题翻译：情绪机器的系统和方法
公开(公告)号：US20110172999A1
公开(公告)日：2011-07-14
申请号：US13053179
申请日：2011-03-21
申请人： Dilek Z. Hakkani-Tur , Jackson J. Liscombe , Guiseppe Riccardi
发明人： Dilek Z. Hakkani-Tur , Jackson J. Liscombe , Guiseppe Riccardi
IPC分类号： G10L15/18 , G10L15/00
CPC分类号： G06F17/274 , G10L15/1807 , G10L17/26
摘要： A system, method and computer-readable medium for practicing a method of emotion detection during a natural language dialog between a human and a computing device are disclosed. The method includes receiving an utterance from a user in a natural language dialog, receiving contextual information regarding the natural language dialog which is related to changes of emotion over time in the dialog, and detecting an emotion of the user based on the received contextual information. Examples of contextual information include, for example, differential statistics, joint statistics and distance statistics.
摘要翻译：公开了一种用于在人与计算设备之间的自然语言对话中练习情感检测方法的系统，方法和计算机可读介质。该方法包括在自然语言对话中从用户接收话语，在对话中接收与随时间推移的情绪变化相关的自然语言对话的上下文信息，以及基于接收到的上下文信息来检测用户的情绪。情境信息的例子包括例如差异统计，联合统计和距离统计。

10. 发明授权

US07957971B2 System and method of spoken language understanding using word confusion networks 有权
标题翻译：使用词混淆网络的口语理解的系统和方法
公开(公告)号：US07957971B2
公开(公告)日：2011-06-07
申请号：US12483853
申请日：2009-06-12
申请人： Allen Louis Gorin , Dilek Z. Hakkani-Tur , Giuseppe Riccardi , Gokhan Tur , Jeremy Huntley Wright
发明人： Allen Louis Gorin , Dilek Z. Hakkani-Tur , Giuseppe Riccardi , Gokhan Tur , Jeremy Huntley Wright
IPC分类号： G10L15/18 , G10L15/00 , G10L15/06 , G10L15/28 , G06F17/27
CPC分类号： G10L15/1822 , G06F17/2775 , G10L15/08
摘要： Word lattices that are generated by an automatic speech recognition system are used to generate a modified word lattice that is usable by a spoken language understanding module. In one embodiment, the spoken language understanding module determines a set of salient phrases by calculating an intersection of the modified word lattice, which is optionally preprocessed, and a finite state machine that includes a plurality of salient grammar fragments.
摘要翻译：由自动语音识别系统生成的词格子用于生成可由口头语言理解模块使用的修改词格。在一个实施例中，口语理解模块通过计算可选地预处理的修改字格点和包括多个显着语法片段的有限状态机的交集来确定一组显着短语。

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