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

US09135237B2 System and a method for generating semantically similar sentences for building a robust SLM 有权
标题翻译：系统和一种用于生成语义上相似的句子来构建稳健的SLM的方法
公开(公告)号：US09135237B2
公开(公告)日：2015-09-15
申请号：US13181923
申请日：2011-07-13
申请人： Om D. Deshmukh , Sachindra Joshi , Shajith I. Mohamed , Ashish Verma
发明人： Om D. Deshmukh , Sachindra Joshi , Shajith I. Mohamed , Ashish Verma
IPC分类号： G06F17/27 , G10L15/26 , G06F17/28
CPC分类号： G06F17/274 , G06F17/2795 , G06F17/2881 , G10L15/26
摘要： A system and method are described for generating semantically similar sentences for a statistical language model. A semantic class generator determines for each word in an input utterance a set of corresponding semantically similar words. A sentence generator computes a set of candidate sentences each containing at most one member from each set of semantically similar words. A sentence verifier grammatically tests each candidate sentence to determine a set of grammatically correct sentences semantically similar to the input utterance. Also note that the generated semantically similar sentences are not restricted to be selected from an existing sentence database.
摘要翻译：描述了用于为统计语言模型生成语义上类似的句子的系统和方法。语义类生成器确定输入语义中的每个单词一组相应的语义上相似的单词。句子生成器从每个语义上相似的单词集合中计算出一组候选句子，每个候选句子最多包含一个成员。句子验证器语法测试每个候选句子以确定一组语法上正确的句子，其语义上类似于输入的话语。还要注意，生成的语义上相似的句子不限于从现有句子数据库中选择。

2. 发明申请

US20130018649A1 System and a Method for Generating Semantically Similar Sentences for Building a Robust SLM 有权
标题翻译：用于生成语义类似句子的系统和方法，用于构建稳健的SLM
公开(公告)号：US20130018649A1
公开(公告)日：2013-01-17
申请号：US13181923
申请日：2011-07-13
申请人： Om D. Deshmukh , Sachindra Joshi , Shajith I. Mohamed , Ashish Verma
发明人： Om D. Deshmukh , Sachindra Joshi , Shajith I. Mohamed , Ashish Verma
IPC分类号： G06F17/27
CPC分类号： G06F17/274 , G06F17/2795 , G06F17/2881 , G10L15/26
摘要： A system and method are described for generating semantically similar sentences for a statistical language model. A semantic class generator determines for each word in an input utterance a set of corresponding semantically similar words. A sentence generator computes a set of candidate sentences each containing at most one member from each set of semantically similar words. A sentence verifier grammatically tests each candidate sentence to determine a set of grammatically correct sentences semantically similar to the input utterance. Also note that the generated semantically similar sentences are not restricted to be selected from an existing sentence database.
摘要翻译：描述了用于为统计语言模型生成语义上类似的句子的系统和方法。语义类生成器确定输入语义中的每个单词一组相应的语义上相似的单词。句子生成器从每个语义上相似的单词集合中计算出一组候选句子，每个候选句子最多包含一个成员。句子验证器语法测试每个候选句子以确定一组语法上正确的句子，其语义上类似于输入的话语。还要注意，生成的语义上相似的句子不限于从现有句子数据库中选择。

3. 发明授权

US08676580B2 Automatic speech and concept recognition 失效
标题翻译：自动语音和概念识别
公开(公告)号：US08676580B2
公开(公告)日：2014-03-18
申请号：US13210471
申请日：2011-08-16
申请人： Om D. Deshmukh , Etienne Marcheret , Shajith I. Mohamed , Ashish Verma , Karthik Visweswariah
发明人： Om D. Deshmukh , Etienne Marcheret , Shajith I. Mohamed , Ashish Verma , Karthik Visweswariah
IPC分类号： G10L15/00 , G10L17/00 , G10L15/14 , G06F17/27
CPC分类号： G10L15/197 , G10L15/193
摘要： A method, an apparatus and an article of manufacture for automatic speech recognition. The method includes obtaining at least one language model word and at least one rule-based grammar word, determining an acoustic similarity of at least one pair of language model word and rule-based grammar word, and increasing a transition cost to the at least one language model word based on the acoustic similarity of the at least one language model word with the at least one rule-based grammar word to generate a modified language model for automatic speech recognition.
摘要翻译：一种用于自动语音识别的方法，装置和制品。该方法包括获得至少一个语言模型词和至少一个基于规则的语法词，确定至少一对语言模型词和基于规则的语法单词的声学相似度，以及增加至少一个基于所述至少一个语言模型词与所述至少一个基于规则的语法词的声学相似性来生成用于自动语音识别的修改语言模型的语言模型词。

4. 发明申请

US20130046539A1 Automatic Speech and Concept Recognition 失效
标题翻译：自动语音和概念识别
公开(公告)号：US20130046539A1
公开(公告)日：2013-02-21
申请号：US13210471
申请日：2011-08-16
申请人： Om D. Deshmukh , Etienne Marcheret , Shajith I. Mohamed , Ashish Verma , Karthik Visweswariah
发明人： Om D. Deshmukh , Etienne Marcheret , Shajith I. Mohamed , Ashish Verma , Karthik Visweswariah
IPC分类号： G10L15/22
CPC分类号： G10L15/197 , G10L15/193
摘要： A method, an apparatus and an article of manufacture for automatic speech recognition. The method includes obtaining at least one language model word and at least one rule-based grammar word, determining an acoustic similarity of at least one pair of language model word and rule-based grammar word, and increasing a transition cost to the at least one language model word based on the acoustic similarity of the at least one language model word with the at least one rule-based grammar word to generate a modified language model for automatic speech recognition.
摘要翻译：一种用于自动语音识别的方法，装置和制品。该方法包括获得至少一个语言模型词和至少一个基于规则的语法词，确定至少一对语言模型词和基于规则的语法单词的声学相似度，以及增加至少一个基于所述至少一个语言模型词与所述至少一个基于规则的语法词的声学相似性来生成用于自动语音识别的修改语言模型的语言模型词。

5. 发明申请

US20130339021A1 Intent Discovery in Audio or Text-Based Conversation 有权
标题翻译：在音频或基于文本的对话中的意图发现
公开(公告)号：US20130339021A1
公开(公告)日：2013-12-19
申请号：US13526637
申请日：2012-06-19
申请人： Om D. Deshmukh , Sachindra Joshi , Saurabh Saket , Ashish Verma
发明人： Om D. Deshmukh , Sachindra Joshi , Saurabh Saket , Ashish Verma
IPC分类号： G10L15/18
CPC分类号： G10L25/48 , G10L15/02 , G10L15/18 , G10L15/1822 , G10L15/26 , G10L21/10
摘要： Techniques, an apparatus and an article of manufacture identifying one or more utterances that are likely to carry the intent of a speaker, from a conversation between two or more parties. A method includes obtaining an input of a set of utterances in chronological order from a conversation between two or more parties, computing an intent confidence value of each utterance by summing intent confidence scores from each of the constituent words of the utterance, wherein intent confidence scores capture each word's influence on the subsequent utterances in the conversation based on (i) the uniqueness of the word in the conversation and (ii) the number of times the word subsequently occurs in the conversation, and generating a ranked order of the utterances from highest to lowest intent confidence value, wherein the highest intent value corresponds to the utterance which is most likely to carry intent of the speaker.
摘要翻译：从两个或多个方之间的对话中识别出可能携带说话人意图的一个或多个话语的技术，装置和制品。一种方法包括从两个或更多方之间的会话按时间顺序获得一组话语的输入，通过将来自每个话语的组成词的意图置信度得分相加来计算每个话语的意图置信度值，其中意图置信度得分基于（i）会话中的单词的唯一性和（ii）单词随后在会话中发生的次数，并且从最高级别生成排序的话语顺序，从而捕获每个单词对对话中后续话语的影响到最低意图置信度值，其中最高意图值对应于最有可能携带说话者意图的话语。

6. 发明申请

US20100185648A1 ENABLING ACCESS TO INFORMATION ON A WEB PAGE 审中-公开
标题翻译：启用对网页上的信息的访问
公开(公告)号：US20100185648A1
公开(公告)日：2010-07-22
申请号：US12353669
申请日：2009-01-14
申请人： Himanshu Chauhan , Om D. Deshmukh , Vijay Kumar Garg , Sachindra Joshi , Ashish Verma
发明人： Himanshu Chauhan , Om D. Deshmukh , Vijay Kumar Garg , Sachindra Joshi , Ashish Verma
IPC分类号： G06F7/06 , G06F17/30
CPC分类号： G06F3/167 , G06F16/9577 , G10L13/00 , G10L15/26
摘要： Techniques for enabling voice access to information residing on the World Wide Web are provided. The techniques include receiving a query from a user, wherein the query comprises a voice-based request to access information residing on the World Wide Web, identifying one or more websites corresponding to the query, fetching the information from a website, wherein fetching the information comprises executing a hypertext transfer protocol (HTTP) request, organizing the information into a voice-based response and delivering the response to the user.
摘要翻译：提供了能够对驻留在万维网上的信息进行语音访问的技术。这些技术包括从用户接收查询，其中查询包括访问驻留在万维网上的信息的基于语音的请求，识别与查询相对应的一个或多个网站，从网站获取信息，其中获取信息包括执行超文本传输协议（HTTP）请求，将信息组织成基于语音的响应并将响应传递给用户。

7. 发明授权

US08983840B2 Intent discovery in audio or text-based conversation 有权
标题翻译：音频或基于文本的对话中的意图发现
公开(公告)号：US08983840B2
公开(公告)日：2015-03-17
申请号：US13526637
申请日：2012-06-19
申请人： Om D. Deshmukh , Sachindra Joshi , Saket Saurabh , Ashish Verma
发明人： Om D. Deshmukh , Sachindra Joshi , Saket Saurabh , Ashish Verma
IPC分类号： G10L15/18 , G06F17/27
CPC分类号： G10L25/48 , G10L15/02 , G10L15/18 , G10L15/1822 , G10L15/26 , G10L21/10
摘要： Techniques, an apparatus and an article of manufacture identifying one or more utterances that are likely to carry the intent of a speaker, from a conversation between two or more parties. A method includes obtaining an input of a set of utterances in chronological order from a conversation between two or more parties, computing an intent confidence value of each utterance by summing intent confidence scores from each of the constituent words of the utterance, wherein intent confidence scores capture each word's influence on the subsequent utterances in the conversation based on (i) the uniqueness of the word in the conversation and (ii) the number of times the word subsequently occurs in the conversation, and generating a ranked order of the utterances from highest to lowest intent confidence value, wherein the highest intent value corresponds to the utterance which is most likely to carry intent of the speaker.
摘要翻译：从两个或多个方之间的对话中识别出可能携带说话人意图的一个或多个话语的技术，装置和制品。一种方法包括从两个或更多方之间的会话按时间顺序获得一组话语的输入，通过将来自每个话语的组成词的意图置信度得分相加来计算每个话语的意图置信度值，其中意图置信度得分基于（i）会话中的单词的唯一性和（ii）单词随后在会话中发生的次数，并且从最高级别生成排序的话语顺序，从而捕获每个单词对对话中后续话语的影响到最低意图置信度值，其中最高意图值对应于最有可能携带说话者意图的话语。

8. 发明授权

US08457967B2 Automatic evaluation of spoken fluency 有权
标题翻译：自动评价口语流利
公开(公告)号：US08457967B2
公开(公告)日：2013-06-04
申请号：US12541927
申请日：2009-08-15
申请人： Kartik Audhkhasi , Om D. Deshmukh , Kundan Kandhway , Ashish Verma
发明人： Kartik Audhkhasi , Om D. Deshmukh , Kundan Kandhway , Ashish Verma
IPC分类号： G10L15/04 , G10L15/26 , G10L15/06 , G10L13/00 , G10L21/00 , G06F17/27
CPC分类号： G10L15/26 , G09B19/04
摘要： A procedure to automatically evaluate the spoken fluency of a speaker by prompting the speaker to talk on a given topic, recording the speaker's speech to get a recorded sample of speech, and then analyzing the patterns of disfluencies in the speech to compute a numerical score to quantify the spoken fluency skills of the speakers. The numerical fluency score accounts for various prosodic and lexical features, including formant-based filled-pause detection, closely-occurring exact and inexact repeat N-grams, normalized average distance between consecutive occurrences of N-grams. The lexical features and prosodic features are combined to classify the speaker with a C-class classification and develop a rating for the speaker.
摘要翻译：一个程序，通过提示说话者在给定的主题上进行谈话，记录讲话者的语音以获得记录的语音样本，然后分析语音中的不清楚的模式以计算数字得分，自动评估讲话者的口语流畅性量化演讲者的口语流利能力。数值流利度分数考虑到各种韵律和词汇特征，包括基于共振峰的填充暂停检测，紧密发生的精确和不精确的重复N克，连续出现的N克之间的归一化平均距离。词汇特征和韵律特征相结合，将扬声器分类为C级分类，并为扬声器开发评级。

9. 发明申请

US20110196677A1 Analysis of the Temporal Evolution of Emotions in an Audio Interaction in a Service Delivery Environment 有权
标题翻译：分析服务交付环境中音频交互情绪的时间演化
公开(公告)号：US20110196677A1
公开(公告)日：2011-08-11
申请号：US12704172
申请日：2010-02-11
申请人： Om D. Deshmukh , Chitra Dorai , Shailesh Joshi , Maureen E. Rzasa , Ashish Verma , Karthik Visweswariah , Gary J. Wright , Sai Zeng
发明人： Om D. Deshmukh , Chitra Dorai , Shailesh Joshi , Maureen E. Rzasa , Ashish Verma , Karthik Visweswariah , Gary J. Wright , Sai Zeng
IPC分类号： G10L17/00 , G10L15/00
CPC分类号： G10L15/22 , G10L2015/227
摘要： According to one illustrative embodiment, a method is provided for analyzing an audio interaction. At least one change in an emotion of a speaker in an audio interaction and at least one aspect of the audio interaction are identified. The at least one change in an emotion is analyzed in conjunction with the at least one aspect to determine a relationship between the at least one change in an emotion and the at least one aspect, and a result of the analysis is provided.
摘要翻译：根据一个说明性实施例，提供了一种用于分析音频交互的方法。识别音频交互中的扬声器的情感和音频交互的至少一个方面中的至少一个变化。结合至少一个方面来分析情绪中的至少一个改变以确定情绪中的至少一个改变与至少一个方面之间的关系，并且提供分析结果。

10. 发明申请

US20110197206A1 System, Method And Program Product For Analyses Based On Agent-Customer Interactions And Concurrent System Activity By Agents 审中-公开
标题翻译：基于代理 - 客户互动和并发系统活动的代理系统，方法和程序产品
公开(公告)号：US20110197206A1
公开(公告)日：2011-08-11
申请号：US12704002
申请日：2010-02-11
申请人： Om D. Deshmukh , Chitra Dorai , Maureen E. Rzasa , Shailesh Joshi , Ashish Verma , Karthik Visweswariah , Gary J. Wright , Sai Zeng
发明人： Om D. Deshmukh , Chitra Dorai , Maureen E. Rzasa , Shailesh Joshi , Ashish Verma , Karthik Visweswariah , Gary J. Wright , Sai Zeng
IPC分类号： G06F9/44
CPC分类号： G06Q10/06
摘要： A method includes deriving first information from a number of agent-customer interactions in a customer service system, and determining concurrent system activity by the agents in the customer service system, the concurrent system activity occurring at least partially concurrently with the number of agent-customer interactions. The method further includes combining the determined first information and the determined concurrent system activity to determine second information related to one or more of the number of agent-customer interactions, and outputting the second information. Apparatus and program products are also disclosed.
摘要翻译：一种方法包括从客户服务系统中的多个代理 - 客户交互导出第一信息，以及由客户服务系统中的代理确定并发系统活动，与代理客户的数量至少部分同时发生的并发系统活动互动该方法还包括将确定的第一信息与所确定的并发系统活动组合以确定与代理 - 客户交互的数量中的一个或多个相关的第二信息，以及输出第二信息。还公开了装置和程序产品。

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