公开(公告)号：US08949132B2

公开(公告)日：2015-02-03

申请号：US14224644

申请日：2014-03-25

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Srinivas Bangalore ,  Junlan Feng ,  Mazin G. Rahim

IPC: G10L15/18 ,  G10L21/00 ,  G06F17/27 ,  G10L25/00 ,  G10L13/08 ,  G10L15/06 ,  H04M3/493 ,  G10L15/22 ,  G10L15/183

CPC classification number: G10L13/08 ,  G06F17/27 ,  G10L15/063 ,  G10L15/183 ,  G10L15/22 ,  H04M3/4936

Abstract: Disclosed is a method for training a spoken dialog service component from website data. Spoken dialog service components typically include an automatic speech recognition module, a language understanding module, a dialog management module, a language generation module and a text-to-speech module. The method includes selecting anchor texts within a website based on a term density, weighting those anchor texts based on a percent of salient words to total words, and incorporating the weighted anchor texts into a live spoken dialog interface, the weights determining a level of incorporation into the live spoken dialog interface.

Abstract translation: 公开了一种从网站数据训练口语对话服务组件的方法。 口语对话服务组件通常包括自动语音识别模块，语言理解模块，对话管理模块，语言生成模块和文本到语音模块。 该方法包括基于术语密度选择网站内的锚文本，基于显着词的百分比将总计文本加权到总词，并将加权的锚文本加入到现场语音对话界面中，权重确定并入级别 进入现场对话界面。

公开(公告)号：US08914294B2

公开(公告)日：2014-12-16

申请号：US14246216

申请日：2014-04-07

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Giuseppe Di Fabbrizio ,  Dilek Z. Hakkani-Tur ,  Mazin G. Rahim ,  Bernard S. Renger ,  Gokhan Tur

IPC: G10L21/00 ,  G10L19/00 ,  G10L15/06 ,  G10L15/22 ,  G10L15/183

CPC classification number: G10L15/063 ,  G10L15/183 ,  G10L15/22

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US20140222426A1

公开(公告)日：2014-08-07

申请号：US14246216

申请日：2014-04-07

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Giuseppe Di Fabbrizio ,  Dilek Z. Hakkani-Tur ,  Mazin G. Rahim ,  Bernard S. Renger ,  Gokhan Tur

IPC: G10L15/06

CPC classification number: G10L15/063 ,  G10L15/183 ,  G10L15/22

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US20140188480A1

公开(公告)日：2014-07-03

申请号：US14196578

申请日：2014-03-04

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Srinivas BANGALORE ,  Junlan Feng ,  Mazin G. Rahim ,  Juergen Schroeter ,  Ann K. Syrdal ,  David Schulz

IPC: G10L13/02

CPC classification number: G10L13/033 ,  G10L13/00 ,  G10L13/02 ,  G10L13/06 ,  G10L13/08 ,  G10L15/197

Abstract: A system and method are disclosed for generating customized text-to-speech voices for a particular application. The method comprises generating a custom text-to-speech voice by selecting a voice for generating a custom text-to-speech voice associated with a domain, collecting text data associated with the domain from a pre-existing text data source and using the collected text data, generating an in-domain inventory of synthesis speech units by selecting speech units appropriate to the domain via a search of a pre-existing inventory of synthesis speech units, or by recording the minimal inventory for a selected level of synthesis quality. The text-to-speech custom voice for the domain is generated utilizing the in-domain inventory of synthesis speech units. Active learning techniques may also be employed to identify problem phrases wherein only a few minutes of recorded data is necessary to deliver a high quality TTS custom voice.

Abstract translation: 公开了用于为特定应用产生定制的文本到语音语音的系统和方法。 该方法包括通过选择用于生成与域相关联的自定义文本到语音语音的语音来生成自定义文本到语音语音，从预先存在的文本数据源收集与域相关联的文本数据，并使用收集的 文本数据，通过搜索合成语音单元的预先存在的库存来选择适合于该域的语音单元，或者通过记录所选合成质量水平的最小库存来生成合成语音单元的域内库存。 使用合成语音单元的域内库存来生成域的文本到语音定制语音。 还可以使用主动学习技术来识别问题短语，其中只需要几分钟的记录数据来传送高质量的TTS定制语音。

公开(公告)号：US20140074477A1

公开(公告)日：2014-03-13

申请号：US14081166

申请日：2013-11-15

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Srinivas Bangalore ,  Narendra K. Gupta ,  Mazin G. Rahim

IPC: G10L15/02 ,  G06F17/27

CPC classification number: G10L15/1815 ,  G06F17/2785 ,  G10L13/043 ,  G10L15/02 ,  G10L15/1822 ,  G10L15/265

Abstract: A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify.

Abstract translation: 公开了一种提高口语对话系统中的自动语音识别的系统和方法。 该方法包括将语音识别器输出划分为独立子句，识别每个自包含子句中的对话行为，通过识别当前域对象和/或当前域动作进行限定对话行为，以及确定是否可进一步限定 对于当前域对象和/或当前域操作。 如果可以进一步鉴定，则该方法包括识别与当前域对象和/或当前域操作相关联的另一域操作和/或另一域对象，将另一域操作和/或另一域对象重新分配为当前域操作，以及 /或当前域对象，然后递归地限定新的当前域操作和/或当前对象。 这个过程一直持续到没有什么是剩下的资格。

公开(公告)号：US20160027434A1

公开(公告)日：2016-01-28

申请号：US14874843

申请日：2015-10-05

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Dilek Z. Hakkani-Tur ,  Mazin G. Rahim ,  Giuseppe Riccardi ,  Gokhan Tur

IPC: G10L15/06 ,  G10L15/26 ,  G10L15/18 ,  G10L15/07

CPC classification number: G10L15/063 ,  G10L15/07 ,  G10L15/18 ,  G10L15/26 ,  G10L2015/0638

Abstract: Utterance data that includes at least a small amount of manually transcribed data is provided. Automatic speech recognition is performed on ones of the utterance data not having a corresponding manual transcription to produce automatically transcribed utterances. A model is trained using all of the manually transcribed data and the automatically transcribed utterances. A predetermined number of utterances not having a corresponding manual transcription are intelligently selected and manually transcribed. Ones of the automatically transcribed data as well as ones having a corresponding manual transcription are labeled. In another aspect of the invention, audio data is mined from at least one source, and a language model is trained for call classification from the mined audio data to produce a language model.

公开(公告)号：US09240177B2

公开(公告)日：2016-01-19

申请号：US14196578

申请日：2014-03-04

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Srinivas Bangalore ,  Junlan Feng ,  Mazin G. Rahim ,  Juergen Schroeter ,  Ann K. Syrdal ,  David Schulz

IPC: G10L13/06 ,  G10L13/08 ,  G10L13/02 ,  G10L13/00

CPC classification number: G10L13/033 ,  G10L13/00 ,  G10L13/02 ,  G10L13/06 ,  G10L13/08 ,  G10L15/197

Abstract: A system and method are disclosed for generating customized text-to-speech voices for a particular application. The method comprises generating a custom text-to-speech voice by selecting a voice for generating a custom text-to-speech voice associated with a domain, collecting text data associated with the domain from a pre-existing text data source and using the collected text data, generating an in-domain inventory of synthesis speech units by selecting speech units appropriate to the domain via a search of a pre-existing inventory of synthesis speech units, or by recording the minimal inventory for a selected level of synthesis quality. The text-to-speech custom voice for the domain is generated utilizing the in-domain inventory of synthesis speech units. Active learning techniques may also be employed to identify problem phrases wherein only a few minutes of recorded data is necessary to deliver a high quality TTS custom voice.

Abstract translation: 公开了用于为特定应用产生定制的文本到语音语音的系统和方法。 该方法包括通过选择用于生成与域相关联的自定义文本到语音语音的语音来生成自定义文本到语音语音，从预先存在的文本数据源收集与域相关联的文本数据，并使用收集的 文本数据，通过搜索合成语音单元的预先存在的库存来选择适合于该域的语音单元，或者通过记录所选合成质量水平的最小库存来生成合成语音单元的域内库存。 使用合成语音单元的域内库存来生成域的文本到语音定制语音。 还可以使用主动学习技术来识别问题短语，其中只需要几分钟的记录数据来传送高质量的TTS定制语音。

公开(公告)号：US20150046159A1

公开(公告)日：2015-02-12

申请号：US14468375

申请日：2014-08-26

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Dilek Z. Hakkani-Tur ,  Mazin G. Rahim ,  Giuseppe Riccardi ,  Gokhan Tur

IPC: G10L15/18 ,  G10L15/26

CPC classification number: G10L15/063 ,  G10L15/07 ,  G10L15/18 ,  G10L15/26 ,  G10L2015/0638

Abstract: Utterance data that includes at least a small amount of manually transcribed data is provided. Automatic speech recognition is performed on ones of the utterance data not having a corresponding manual transcription to produce automatically transcribed utterances. A model is trained using all of the manually transcribed data and the automatically transcribed utterances. A predetermined number of utterances not having a corresponding manual transcription are intelligently selected and manually transcribed. Ones of the automatically transcribed data as well as ones having a corresponding manual transcription are labeled. In another aspect of the invention, audio data is mined from at least one source, and a language model is trained for call classification from the mined audio data to produce a language model.

Abstract translation: 提供了至少包含少量手动转录数据的语音数据。 对没有相应的手动转录的话语数据中的一个进行自动语音识别以产生自动转录的话语。 使用所有手动转录数据和自动转录的话语训练模型。 智能地选择并且手动地转录预定数量的不具有对应的手动转录的话语。 自动转录的数据以及具有相应手动转录的数据的标签。 在本发明的另一方面，音频数据从至少一个源开始，并且语言模型被训练用于从所开采的音频数据进行呼叫分类以产生语言模型。

公开(公告)号：US20140163988A1

公开(公告)日：2014-06-12

申请号：US14182017

申请日：2014-02-17

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Mazin G. Rahim ,  Giuseppe Riccardi ,  Jeremy Huntley Wright ,  Bruce Melvin Buntschuh ,  Allen Louis Gorin

IPC: G10L15/14

CPC classification number: G10L15/142

Abstract: A system and a method are provided. A speech recognition processor receives unconstrained input speech and outputs a string of words. The speech recognition processor is based on a numeric language that represents a subset of a vocabulary. The subset includes a set of words identified as being for interpreting and understanding number strings. A numeric understanding processor contains classes of rules for converting the string of words into a sequence of digits. The speech recognition processor utilizes an acoustic model database. A validation database stores a set of valid sequences of digits. A string validation processor outputs validity information based on a comparison of a sequence of digits output by the numeric understanding processor with valid sequences of digits in the validation database.

Abstract translation: 提供了一种系统和方法。 语音识别处理器接收无约束输入语音并输出一串字。 语音识别处理器基于代表词汇子集的数字语言。 该子集包括被识别为用于解释和理解数字串的一组单词。 数字理解处理器包含用于将字符串转换为数字序列的规则类型。 语音识别处理器使用声学模型数据库。 验证数据库存储一组有效的数字序列。 字符串验证处理器基于数字理解处理器输出的数字序列与验证数据库中的有效数字序列的比较来输出有效性信息。

公开(公告)号：US08671088B2

公开(公告)日：2014-03-11

申请号：US13854582

申请日：2013-04-01

Applicant: AT&T Intellectual Property II, L.P.

Inventor： Richard Vandervoort Cox ,  Hossein Eslambolchi ,  Behzad Nadji ,  Mazin G. Rahim

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/30864 ,  G06F17/30657 ,  G06F17/30663 ,  G06F17/30684 ,  G06N99/005 ,  G10L15/22 ,  G10L21/06

Abstract: A system and method for providing a natural language interface to a database or the Internet. The method provides a response from a database to a natural language query. The method comprises receiving a user query, extracting key data from the user query, submitting the extracted key data to a data base search engine to retrieve a top n pages from the data base, processing of the top n pages through a natural language dialog engine and providing a response based on processing the top n pages.

Abstract translation: 一种用于向数据库或因特网提供自然语言界面的系统和方法。 该方法提供从数据库到自然语言查询的响应。 该方法包括接收用户查询，从用户查询中提取密钥数据，将提取的密钥数据提交给数据库搜索引擎以从数据库中检索最前面的页面，通过自然语言对话引擎处理前n个页面 并提供基于处理前n页的响应。