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. 发明申请

WO2007117814A3 VOICE SIGNAL PERTURBATION FOR SPEECH RECOGNITION 审中-公开
标题翻译：语音识别中的语音信号扰动
公开(公告)号：WO2007117814A3
公开(公告)日：2008-05-22
申请号：PCT/US2007063752
申请日：2007-03-12
申请人： MOTOROLA INC , MA CHANGXUE C
发明人： MA CHANGXUE C
IPC分类号： G10L15/14
CPC分类号： G10L15/20 , G10L21/0216
摘要： A system (100) and method (200) for generating a perturbed phonetic string for use in speech recognition. The method can include generating (202) a feature vector set from a spoken utterance, applying (204) a perturbation to the feature vector set for producing a perturbed feature vector set, and phonetically decoding (206) the perturbed feature vector set for producing a perturbed phonetic string. The perturbation mimics environmental variability and speaker variability for reducing the number of spoken utterances in speech recognition applications.
摘要翻译：一种用于生成用于语音识别的扰动语音串的系统（100）和方法（200）。该方法可以包括：从口头发声生成（202）特征向量组;将特征向量组应用（204）摄动以产生干扰特征向量组;以及发音解码（206）摄动特征向量组以产生扰乱的语音字符串。扰动模拟环境变化和说话者变异性，以减少语音识别应用中说话的次数。

2. 发明申请

WO2007095413A2 METHOD AND APPARATUS FOR DETECTING AFFECTS IN SPEECH 审中-公开
标题翻译：用于检测语音影响的方法和装置
公开(公告)号：WO2007095413A2
公开(公告)日：2007-08-23
申请号：PCT/US2007061114
申请日：2007-01-26
申请人： MOTOROLA INC , MA CHANGXUE C , HUANG RONGQUING
发明人： MA CHANGXUE C , HUANG RONGQUING
CPC分类号： G10L25/48
摘要： A method and apparatus for speaker independent real-time affect detection includes generating (205) a sequence of audio frames from a segment of speech, generating (210) a sequence of feature sets by generating a feature set for each frame, and applying (215) the sequence of feature sets to a sequential classifier to determine a most likely affect expressed in the segment of speech.
摘要翻译：一种用于独立于扬声器的实时影响检测的方法和装置，包括从语音片段生成（205）音频帧序列，通过生成每个帧的特征集合产生（210）特征集序列，并应用）特征集的序列到顺序分类器以确定在语音段中表达的最可能的影响。

3. 发明申请

WO2008115285A2 CONTENT SELECTION USING SPEECH RECOGNITION 审中-公开
标题翻译：使用语音识别的内容选择
公开(公告)号：WO2008115285A2
公开(公告)日：2008-09-25
申请号：PCT/US2007081574
申请日：2007-10-17
申请人： MOTOROLA INC , MA CHANGXUE C , CHENG YAN M
发明人： MA CHANGXUE C , CHENG YAN M
IPC分类号： H01S5/00
CPC分类号： G06F17/30026
摘要： Disclosed are a method and wireless device for selecting a content file using speech recogn
摘要翻译：公开了一种使用语音识别来选择内容文件的方法和无线装置

4. 发明申请

WO2008042511B1 PERSONALIZING A VOICE DIALOGUE SYSTEM 审中-公开
标题翻译：个性化语音对话系统
公开(公告)号：WO2008042511B1
公开(公告)日：2008-12-18
申请号：PCT/US2007076353
申请日：2007-08-21
申请人： MOTOROLA INC , MA CHANGXUE C , CHENG YAN MING , NOWLAN STEVEN J , RUSSELL DALE W , WEI YUAN-JUN
发明人： MA CHANGXUE C , CHENG YAN MING , NOWLAN STEVEN J , RUSSELL DALE W , WEI YUAN-JUN
IPC分类号： H04M1/64 , H04M11/00
CPC分类号： H04M3/4936
摘要： A method (10) and system (200) for personalized voice dialogue can include tracking (12) a user's use of voice dialogue states or transitions and progressively offering (16) a user more efficient voice dialogue transitions or states such as voice dialogue transition or states having fewer and fewer words. The tracking of dialog states or transitions can include tracking (14) of repeated use of the dialogue states or transitions. A user can be prompted to create a new transition or state. The prompting (18) and confirmation and verification (20) by the user of a new transition or state can be done using SCXML language. The method can further include instantiating (21) the new transition or state with voice tags or words and performing (22) speech recognition using the new transition or state. The method can again determine (23) if the new transition or state is a repeat transition or state.
摘要翻译：用于个性化语音对话的方法（10）和系统（200）可以包括跟踪（12）用户对语音对话状态或转换的使用，并逐渐提供（16）用户更高效的语音对话转换或状态，例如语音对话转换或国家的文字越来越少。对话状态或转换的跟踪可以包括跟踪（14）重复使用对话状态或转换。可以提示用户创建新的转换或状态。新的转换或状态的用户的提示（18）和确认和验证（20）可以使用SCXML语言完成。该方法可以进一步包括用语音标签或单词实例化（21）新的转换或状态，并且使用新的转换或状态来执行（22）语音识别。该方法可以再次确定（23）新的转换或状态是否是重复转换或状态。

5. 发明申请

WO2007117814B1 VOICE SIGNAL PERTURBATION FOR SPEECH RECOGNITION 审中-公开
标题翻译：语音信号语音识别
公开(公告)号：WO2007117814B1
公开(公告)日：2008-07-10
申请号：PCT/US2007063752
申请日：2007-03-12
申请人： MOTOROLA INC , MA CHANGXUE C
发明人： MA CHANGXUE C
IPC分类号： G10L15/14
CPC分类号： G10L15/20 , G10L21/0216
摘要： A system (100) and method (200) for generating a perturbed phonetic string for use in speech recognition. The method can include generating (202) a feature vector set from a spoken utterance, applying (204) a perturbation to the feature vector set for producing a perturbed feature vector set, and phonetically decoding (206) the perturbed feature vector set for producing a perturbed phonetic string. The perturbation mimics environmental variability and speaker variability for reducing the number of spoken utterances in speech recognition applications.
摘要翻译：一种用于产生用于语音识别的扰动语音串的系统（100）和方法（200）。该方法可以包括从语音发音生成（202）特征向量集合，将扰动应用（204）扰动到特征向量集合以产生扰动的特征向量集合，并且语音地解码（206）扰动的特征向量集合以产生扰乱的语音字符串扰动模拟环境变异性和说话者变异性，以减少语音识别应用中的口语话语数量。

6. 发明申请

WO2007118020A3 METHOD AND SYSTEM FOR MANAGING PRONUNCIATION DICTIONARIES IN A SPEECH APPLICATION 审中-公开
标题翻译：用于管理语音应用中的发音词典的方法和系统
公开(公告)号：WO2007118020A3
公开(公告)日：2008-05-08
申请号：PCT/US2007065466
申请日：2007-03-29
申请人： MOTOROLA INC , GROBLE MICHAEL E , MA CHANGXUE C
发明人： GROBLE MICHAEL E , MA CHANGXUE C
IPC分类号： G10L13/08
CPC分类号： G10L15/187 , G10L13/08
摘要： A voice toolkit (100) and a method (700) for managing pronunciation dictionaries are provided. The visual toolkit can include a user-interface (110) for entering in a text and a corresponding spoken utterance, a text-to-speech system (120) for synthesizing a pronunciation from the text, a talking speech recognizer (132) for generating pronunciations of the spoken utterance, and a voice processor (130) for validating at least one pronunciation. A developer can type a text of a word into the toolkit and listen to the pronunciation to determine whether the pronunciation is acceptable. If the pronunciation is incorrect the developer can speak the word for providing a spoken utterance having a correct pronunciation.
摘要翻译：提供了一种用于管理发音词典的语音工具包（100）和方法（700）。可视化工具包可以包括用于输入文本的用户界面（110）和对应的说话话语，用于从文本合成发音的文本到语音系统（120），用于生成语音识别器（132）的通话语音识别器讲话语音的发音，以及用于验证至少一个发音的语音处理器（130）。开发人员可以在工具包中输入单词的文字，并听发音来确定发音是否可以接受。如果发音不正确，开发人员可以说出提供具有正确发音的口语发音。

7. 发明申请

WO2008042511A3 PERSONALIZING A VOICE DIALOGUE SYSTEM 审中-公开
标题翻译：个性化语音对话系统
公开(公告)号：WO2008042511A3
公开(公告)日：2008-10-30
申请号：PCT/US2007076353
申请日：2007-08-21
申请人： MOTOROLA INC , MA CHANGXUE C , CHENG YAN MING , NOWLAN STEVEN J , RUSSELL DALE W , WEI YUAN-JUN
发明人： MA CHANGXUE C , CHENG YAN MING , NOWLAN STEVEN J , RUSSELL DALE W , WEI YUAN-JUN
IPC分类号： H04M1/64 , H04M11/00
CPC分类号： H04M3/4936
摘要： A method (10) and system (200) for personalized voice dialogue can include tracking (12) a user's use of voice dialogue states or transitions and progressively offering (16) a user more efficient voice dialogue transitions or states such as voice dialogue transition or states having fewer and fewer words. The tracking of dialog states or transitions can include tracking (14) of repeated use of the dialogue states or transitions. A user can be prompted to create a new transition or state. The prompting (18) and confirmation and verification (20) by the user of a new transition or state can be done using SCXML language. The method can further include instantiating (21) the new transition or state with voice tags or words and performing (22) speech recognition using the new transition or state. The method can again determine (23) if the new transition or state is a repeat transition or state.
摘要翻译：用于个性化语音对话的方法（10）和系统（200）可以包括跟踪（12）用户对语音对话状态或转换的使用，并逐渐提供（16）用户更有效的语音对话转换或状态，例如语音对话转换或状态越来越少的单词。跟踪对话状态或转换可以包括跟踪（14）重复使用对话状态或转换。可以提示用户创建新的转换或状态。用户可以使用SCXML语言完成新的转换或状态的提示（18）和确认（20）。该方法还可以包括使用语音标签或单词实例化（21）新的转换或状态，并使用新的转换或状态执行（22）语音识别。该方法可以再次确定（23）如果新的转换或状态是重复转换或状态。

8. 发明申请

WO2006107586A3 METHOD AND SYSTEM FOR INTERPRETING VERBAL INPUTS IN A MULTIMODAL DIALOG SYSTEM 审中-公开
标题翻译：用于在多模对话系统中解释VERBAL输入的方法和系统
公开(公告)号：WO2006107586A3
公开(公告)日：2007-03-08
申请号：PCT/US2006010208
申请日：2006-03-20
申请人： MOTOROLA INC , MA CHANGXUE C , BLISS HARRY M , CHENG YAN M
发明人： MA CHANGXUE C , BLISS HARRY M , CHENG YAN M
IPC分类号： G10L15/18
CPC分类号： G06F17/279 , G06F3/038 , G06F2203/0381 , G10L15/1815
摘要： A method, a system and a computer program product for interpreting a verbal input in a multimodal dialog system are provided. The method includes assigning (302) a confidence value to at least one word generated by a verbal recognition component. The method further includes generating (304) a semantic unit confidence score for the verbal input. The generation of a semantic unit confidence score is based on the confidence value of at least one word and at least one semantic confidence operator.
摘要翻译：提供了一种用于在多模式对话系统中解释口头输入的方法，系统和计算机程序产品。该方法包括将置信度值（302）分配（302）至由语言识别组件生成的至少一个词。该方法还包括为语言输入生成（304）语义单位置信度得分。语义单位置信度得分的产生基于至少一个单词和至少一个语义置信度运算符的置信度值。

9. 发明申请

WO2007067837A3 VOICE QUALITY CONTROL FOR HIGH QUALITY SPEECH RECONSTRUCTION 审中-公开
标题翻译：高品质语音重建的语音质量控制
公开(公告)号：WO2007067837A3
公开(公告)日：2008-06-05
申请号：PCT/US2006060935
申请日：2006-11-15
申请人： MOTOROLA INC , MA CHANGXUE C , CHENG YAN M , NOWLAN STEVEN J , RAMABADRAN TENKASI V
发明人： MA CHANGXUE C , CHENG YAN M , NOWLAN STEVEN J , RAMABADRAN TENKASI V
IPC分类号： G10L15/04
CPC分类号： G10L25/69 , G10L15/26
摘要： A method and apparatus are provided for reproducing a speech sequence of a user through a communication device of the user. The method includes the steps of detecting a speech sequence from the user through the communication device, recognizing a phoneme sequence within the detected speech sequence and forming a confidence level of each phoneme within the recognized phoneme sequence. The method further includes the steps of audibly reproducing the recognized phoneme sequence for the user through the communication device and gradually highlighting or degrading a voice quality of at least some phonemes of the recognized phoneme sequence based upon the formed confidence level of the at least some phonemes.
摘要翻译：提供了一种用于通过用户的通信设备再现用户的语音序列的方法和装置。该方法包括以下步骤：通过通信设备检测来自用户的语音序列，识别检测到的语音序列内的音素序列，并形成识别的音素序列内每个音素的置信度。该方法还包括以下步骤：通过通信设备可听地再现用户的识别音素序列，并且基于形成的至少一些音素的置信水平逐渐突出或降低所识别的音素序列的至少一些音素的语音质量。

10. 发明申请

WO2007095413B1 METHOD AND APPARATUS FOR DETECTING AFFECTS IN SPEECH 审中-公开
标题翻译：用于检测演讲中的影响的方法和设备
公开(公告)号：WO2007095413B1
公开(公告)日：2008-05-22
申请号：PCT/US2007061114
申请日：2007-01-26
申请人： MOTOROLA INC , MA CHANGXUE C , HUANG RONGQUING
发明人： MA CHANGXUE C , HUANG RONGQUING
IPC分类号： G10L15/00
CPC分类号： G10L25/48
摘要： A method and apparatus for speaker independent real-time affect detection includes generating (205) a sequence of audio frames from a segment of speech, generating (210) a sequence of feature sets by generating a feature set for each frame, and applying (215) the sequence of feature sets to a sequential classifier to determine a most likely affect expressed in the segment of speech.
摘要翻译：一种用于说话者独立实时影响检测的方法和设备包括：从语音段生成（205）音频帧序列;通过生成（210）特征集序列，生成每帧特征集;以及应用（215））将特征集的序列分配给顺序分类器以确定在该段中表达的最可能的影响。

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