利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

86 条记录 (耗时 0.04 秒)

    Method and apparatus for the recognition of spelled spoken words
    1.
    发明授权
    Method and apparatus for the recognition of spelled spoken words 有权
    用于识别拼写的口语的方法和装置

    公开(公告)号：US06694296B1

    公开(公告)日：2004-02-17

    申请号：US09706375

    申请日：2000-11-03

    申请人： Fileno A. Alleva ,  Mei-Yuh Hwang ,  Yun-Cheng Ju

    发明人： Fileno A. Alleva ,  Mei-Yuh Hwang ,  Yun-Cheng Ju

    IPC分类号： G10L1528

    CPC分类号： G10L15/197 ,  G10L2015/086

    摘要： The speech recognizer includes a dictation language model providing a dictation model output indicative of a likely word sequence recognized based on an input utterance. A spelling language model provides a spelling model output indicative of a likely letter sequence recognized based on the input utterance. An acoustic model provides an acoustic model output indicative of a likely speech unit recognized based on the input utterances. A speech recognition component is configured to access the dictation language model, the spelling language model and the acoustic model. The speech recognition component weights the dictation model output and the spelling model output in calculating likely recognized speech based on the input utterance. The speech recognizer can also be configured to confine spelled speech to an active lexicon.

    摘要翻译： 语音识别器包括提供语言模型输出的听写语言模型，所述听写模型输出指示基于输入语音识别的可能的单词序列。 拼写语言模型提供了拼写模型输出，其指示基于输入话语识别的可能字母序列。 声学模型提供指示基于输入的话语识别的可能语音单元的声学模型输出。 语音识别组件被配置为访问听写语言模型，拼写语言模型和声学模型。 语音识别组件基于输入的话语来计算听写模型输出和拼写模型输出，以计算可能识别的语音。 语音识别器还可以被配置为将拼写的语音限制在活动词典中。

    Method and system for dynamically adjusted training for speech recognition
    2.
    发明授权
    Method and system for dynamically adjusted training for speech recognition 失效
    用于语音识别的动态调整训练的方法和系统

    公开(公告)号：US5963903A

    公开(公告)日：1999-10-05

    申请号：US673435

    申请日：1996-06-28

    申请人： Hsiao-Wuen Hon ,  Xuedong D. Huang ,  Mei-Yuh Hwang ,  Li Jiang ,  Yun-Cheng Ju ,  Milind V. Mahajan ,  Michael J. Rozak

    发明人： Hsiao-Wuen Hon ,  Xuedong D. Huang ,  Mei-Yuh Hwang ,  Li Jiang ,  Yun-Cheng Ju ,  Milind V. Mahajan ,  Michael J. Rozak

    IPC分类号： G10L15/02 ,  G10L15/06 ,  G10L15/14 ,  G10L5/04

    CPC分类号： G10L15/063 ,  G10L2015/0635

    摘要： A method and system for dynamically selecting words for training a speech recognition system. The speech recognition system models each phoneme using a hidden Markov model and represents each word as a sequence of phonemes. The training system ranks each phoneme for each frame according to the probability that the corresponding codeword will be spoken as part of the phoneme. The training system collects spoken utterances for which the corresponding word is known. The training system then aligns the codewords of each utterance with the phoneme that it is recognized to be part of. The training system then calculates an average rank for each phoneme using the aligned codewords for the aligned frames. Finally, the training system selects words for training that contain phonemes with a low rank.

    摘要翻译： 一种用于动态选择用于训练语音识别系统的单词的方法和系统。 语音识别系统使用隐马尔科夫模型对每个音素进行建模，并将每个单词表示为音素序列。 训练系统根据将相应的码字作为音素的一部分被说出的概率，对每个帧的每个音素进行排序。 训练系统收集对应词语已知的口语说话。 然后，训练系统将每个话语的码字与被认为是其一部分的音素对齐。 训练系统然后使用对齐的帧的对齐码字来计算每个音素的平均等级。 最后，训练系统选择包含低等级音素的训练词。

    Spoken utterance classification training for a speech recognition system
    3.
    发明授权
    Spoken utterance classification training for a speech recognition system 有权
    语音识别系统讲话分类训练

    公开(公告)号：US09082403B2

    公开(公告)日：2015-07-14

    申请号：US13326659

    申请日：2011-12-15

    申请人： Yun-Cheng Ju ,  James Garnet Droppo, III

    发明人： Yun-Cheng Ju ,  James Garnet Droppo, III

    IPC分类号： G10L15/00 ,  G10L15/18

    CPC分类号： G10L15/1822

    摘要： The subject disclosure is directed towards training a classifier for spoken utterances without relying on human-assistance. The spoken utterances may be related to a voice menu program for which a speech comprehension component interprets the spoken utterances into voice menu options. The speech comprehension component provides confirmations to some of the spoken utterances in order to accurately assign a semantic label. For each spoken utterance with a denied confirmation, the speech comprehension component automatically generates a pseudo-semantic label that is consistent with the denied confirmation and selected from a set of potential semantic labels and updates a classification model associated with the classifier using the pseudo-semantic label.

    摘要翻译： 主题披露旨在培训用于讲话的分类器，而不依赖人力援助。 讲话话语可能与语音菜单程序相关，语音理解组件将语音话语解释成语音菜单选项。 语音理解组件为一些语音语音提供了确认，以便准确地分配语义标签。 对于每个具有拒绝确认的口语说话，语音理解组件自动生成与拒绝确认一致的伪语义标签，并从一组潜在语义标签中选择，并使用伪语义更新与分类器相关联的分类模型 标签。

    CONFIDENCE MEASURE GENERATION FOR SPEECH RELATED SEARCHING
    4.
    发明申请
    CONFIDENCE MEASURE GENERATION FOR SPEECH RELATED SEARCHING 有权
    用于语音相关搜索的信心度量产生

    公开(公告)号：US20120185252A1

    公开(公告)日：2012-07-19

    申请号：US13428917

    申请日：2012-03-23

    申请人： Ye-Yi Wang ,  Yun-Cheng Ju ,  Dong Yu

    发明人： Ye-Yi Wang ,  Yun-Cheng Ju ,  Dong Yu

    IPC分类号： G10L15/04

    CPC分类号： G10L15/1822

    摘要： A method of generating a confidence measure generator is provided for use in a voice search system, the voice search system including voice search components comprising a speech recognition system, a dialog manager and a search system. The method includes selecting voice search features, from a plurality of the voice search components, to be considered by the confidence measure generator in generating a voice search confidence measure. The method includes training a model, using a computer processor, to generate the voice search confidence measure based on selected voice search features.

    摘要翻译： 提供了一种产生置信度量产生器的方法，用于语音搜索系统中，该语音搜索系统包括包括语音识别系统，对话管理器和搜索系统的语音搜索组件。 该方法包括从多个语音搜索组件中选择语音搜索特征，以由置信度量产生器在生成语音搜索置信度量时考虑。 该方法包括使用计算机处理器来训练模型，以基于所选择的语音搜索特征生成语音搜索置信度度量。

    MULTI-MODAL QUERY GENERATION
    5.
    发明申请
    MULTI-MODAL QUERY GENERATION 审中-公开
    多模式查询生成

    公开(公告)号：US20090287626A1

    公开(公告)日：2009-11-19

    申请号：US12200648

    申请日：2008-08-28

    申请人： Timothy Seung Yoon Paek ,  Bo Thiesson ,  Yun-Cheng Ju ,  Bongshin Lee ,  Christopher A. Meek

    发明人： Timothy Seung Yoon Paek ,  Bo Thiesson ,  Yun-Cheng Ju ,  Bongshin Lee ,  Christopher A. Meek

    IPC分类号： G06F7/06 ,  G06F17/30 ,  G06N5/02

    CPC分类号： G06F16/3322 ,  G10L15/26

    摘要： A multi-modal search system (and corresponding methodology) is provided. The system employs text, speech, touch and gesture input to establish a search query. Additionally, a subset of the modalities can be used to obtain search results based upon exact or approximate matches to a search result. For example, wildcards, which can either be triggered by the user or inferred by the system, can be employed in the search.

    摘要翻译： 提供了一种多模式搜索系统（及相应的方法）。 系统采用文字，语音，触摸和手势输入建立搜索查询。 此外，模态的子集可以用于基于与搜索结果的精确或近似匹配来获得搜索结果。 例如，可以由用户触发或由系统推断的通配符可用于搜索。

    PERSONAL POINTS OF INTEREST IN LOCATION-BASED APPLICATIONS
    6.
    发明申请
    PERSONAL POINTS OF INTEREST IN LOCATION-BASED APPLICATIONS 审中-公开
    基于位置的应用程序的个人兴趣点

    公开(公告)号：US20090082037A1

    公开(公告)日：2009-03-26

    申请号：US11860433

    申请日：2007-09-24

    申请人： Yun-Cheng Ju ,  Michael Seltzer ,  Ivan J. Tashev

    发明人： Yun-Cheng Ju ,  Michael Seltzer ,  Ivan J. Tashev

    IPC分类号： H04Q7/20

    CPC分类号： G01C21/3608 ,  G01C21/3679 ,  H04L67/18

    摘要： Framework for receiving, processing, and re-using personal points of interest (PPOI) information of a user in a location-based application. A telephone dialog system provides location-based information related PPOI of a user. For example, the PPOI information can include major intersections that the user may normally travel, gas stations, clubs, etc., based on real-time data obtained via web services. The PPOI information can be acquired using common names and nicknames, which are added into system lexicon and recognition grammars. Each PPOI is also tagged to the user (or “owner”) who defined it. The PPOI information can also be shared to support a community of users. The framework also resolves conflicting PPOI information between multiple users and multiple locations. PPOI information input by one user can be used to extract demographic information and personal preferences and be re-used by other users by automatically popping up common names and attributes other users entered for the same nickname.

    摘要翻译： 用于在基于位置的应用程序中接收，处理和重新使用用户的个人兴趣点（PPOI）信息的框架。 电话对话系统提供用户的基于位置的信息相关的PPOI。 例如，PPOI信息可以包括基于通过web服务获得的实时数据，用户可能正常旅行的主要交叉路口，加油站，俱乐部等。 可以使用通用名称和昵称来获取PPOI信息，这些名称和昵称被添加到系统词典和识别语法中。 每个PPOI也被标记给定义它的用户（或“所有者”）。 PPOI信息也可以共享，以支持用户社区。 该框架还解决了多个用户和多个位置之间的冲突的PPOI信息。 一个用户输入的PPOI信息可以用于提取人口统计信息和个人偏好，并通过自动弹出其他用户为相同昵称输入的公用名称和属性，由其他用户重新使用。

    Indexing and ranking processes for directory assistance services
    7.
    发明申请
    Indexing and ranking processes for directory assistance services 有权
    目录援助服务的索引和排名流程

    公开(公告)号：US20080172376A1

    公开(公告)日：2008-07-17

    申请号：US11652733

    申请日：2007-01-12

    申请人： Dong Yu ,  Alejandro Acero ,  Yun-Cheng Ju ,  Ye-Yi Wang

    发明人： Dong Yu ,  Alejandro Acero ,  Yun-Cheng Ju ,  Ye-Yi Wang

    IPC分类号： G06F17/30

    CPC分类号： G06F17/30663 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99942

    摘要： A computer-implemented method is disclosed for providing a directory assistance service. The method includes generating an indexing file that is a representation of information associated with a collection of listings stored in an index. The indexing file is utilized as a basis for ranking listings in an index based on the strength of association with a query. Based at least in part on the ranking, an output is provided and is indicative of listings in the index that are likely correspond to the query. At least one particular listing in the index is excluded from the output without there ever being a comparison of features in the query with features in the one particular listing.

    摘要翻译： 公开了一种用于提供目录辅助服务的计算机实现的方法。 该方法包括生成索引文件，其是与存储在索引中的列表的集合相关联的信息的表示。 基于与查询的关联强度，索引文件被用作在索引中对列表进行排名的基础。 至少部分地基于排名，提供输出并且指示索引中可能对应于查询的列表。 索引中的至少一个特定列表从输出中排除，而不会将查询中的功能与特定列表中的功能进行比较。

    Homonym processing in the context of voice-activated command systems
    10.
    发明申请
    Homonym processing in the context of voice-activated command systems 有权
    在语音激活的命令系统的上下文中进行同义词处理

    公开(公告)号：US20060004572A1

    公开(公告)日：2006-01-05

    申请号：US10935679

    申请日：2004-09-07

    申请人： Yun-Cheng Ju ,  David Ollason ,  Siddharth Bhatia

    发明人： Yun-Cheng Ju ,  David Ollason ,  Siddharth Bhatia

    IPC分类号： G10L15/06

    CPC分类号： G10L15/187 ,  G10L15/06

    摘要： A method is disclosed from constructing a grammar. The grammar is configured to be processed by a speech recognition engine in the context of a voice-activated command system. The method includes receiving a database containing a plurality of terms. From the plurality of terms, first and second terms are identified. The first and second terms are spelled differently but have a first pronunciation in common. One of the first and second terms also has a second pronunciation that is not inherent to the other of the first and second terms. The first and second pronunciations are placed within the grammar.

    摘要翻译： 从构造语法中公开了一种方法。 在语音激活的命令系统的上下文中，语法被配置为由语音识别引擎处理。 该方法包括接收包含多个项的数据库。 从多个术语中，识别第一和第二项。 第一和第二个术语拼写不同，但第一个共同的发音。 第一和第二术语中的一个也具有第二和第二术语中另一个固有的第二发音。 第一和第二个发音被放置在语法内。