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

US20140025381A1 EVALUATING TEXT-TO-SPEECH INTELLIGIBILITY USING TEMPLATE CONSTRAINED GENERALIZED POSTERIOR PROBABILITY 审中-公开
标题翻译：使用模板约束的一般化后验概率评估文本到语音智能
公开(公告)号：US20140025381A1
公开(公告)日：2014-01-23
申请号：US13554480
申请日：2012-07-20
申请人： Linfang Wang , Yan Teng , Lijuan Wang , Frank Kao-Ping Soong , Zhe Geng , William Brad Waller , Mark Tillman Hanson
发明人： Linfang Wang , Yan Teng , Lijuan Wang , Frank Kao-Ping Soong , Zhe Geng , William Brad Waller , Mark Tillman Hanson
IPC分类号： G10L13/08
CPC分类号： G10L25/69 , G10L13/00
摘要： Instead of relying on humans to subjectively evaluate speech intelligibility of a subject, a system objectively evaluates the speech intelligibility. The system receives speech input and calculates confidence scores at multiple different levels using a Template Constrained Generalized Posterior Probability algorithm. One or multiple intelligibility classifiers are utilized to classify the desired entities on an intelligibility scale. A specific intelligibility classifier utilizes features such as the various confidence scores. The scale of the intelligibility classification can be adjusted to suit the application scenario. Based on the confidence score distributions and the intelligibility classification results at multiple levels an overall objective intelligibility score is calculated. The objective intelligibility scores can be used to rank different subjects or systems being assessed according to their intelligibility levels. The speech that is below a predetermined intelligibility (e.g. utterances with low confidence scores and most severe intelligibility issues) can be automatically selected for further analysis.
摘要翻译：系统客观地评估语言的可懂度，而不是依靠人类来主观地评估一个主题的语音清晰度。系统接收语音输入，并使用模板约束广义后验概率算法在多个不同级别计算置信度分数。一个或多个可理解性分类器用于在可懂度量表上分类所需实体。特定的清晰度分类器利用各种置信度分数等特征。可以调整可懂度分类的规模，以适应应用场景。基于多个级别的置信度分数和可理解性分类结果，计算出总目标可懂度分数。客观可理解性分数可用于根据其可理解性级别对待评估的不同科目或系统进行排名。可以自动选择低于预定清晰度（例如具有低置信度得分和最严重的可理解性问题的话语）的语音用于进一步分析。

2. 发明申请

US20120116761A1 Minimum Converted Trajectory Error (MCTE) Audio-to-Video Engine 有权
标题翻译：最小转换轨迹误差（MCTE）音频到视频引擎
公开(公告)号：US20120116761A1
公开(公告)日：2012-05-10
申请号：US12939528
申请日：2010-11-04
申请人： Lijuan Wang , Frank Kao-Ping Soong
发明人： Lijuan Wang , Frank Kao-Ping Soong
IPC分类号： G10L15/00
CPC分类号： G10L21/06 , G10L21/10 , G10L2021/105
摘要： Embodiments of an audio-to-video engine are disclosed. In operation, the audio-to-video engine generates facial movement (e.g., a virtual talking head) based on an input speech. The audio-to-video engine receives the input speech and recognizes the input speech as a source feature vector. The audio-to-video engine then determines a Maximum A Posterior (MAP) mixture sequence based on the source feature vector. The MAP mixture sequence may be a function of a refined Gaussian Mixture Model (GMM). The audio-to-video engine may then use the MAP to estimate video feature parameters. The video feature parameters are then interpreted as facial movement. The facial movement may be stored as data to a storage module and/or it may be displayed as video to a display device.
摘要翻译：公开了音频到视频引擎的实施例。在操作中，音频到视频引擎基于输入语音产生面部动作（例如，虚拟通话头）。音频到视频引擎接收输入语音并将输入语音识别为源特征向量。音频到视频引擎然后基于源特征向量确定最大后验（MAP）混合序列。 MAP混合序列可以是精细高斯混合模型（GMM）的函数。音频到视频引擎然后可以使用MAP估计视频特征参数。视频功能参数被解释为面部动作。面部运动可以作为数据存储到存储模块和/或其可以作为视频显示到显示装置。

3. 发明授权

US08583438B2 Unnatural prosody detection in speech synthesis 有权
公开(公告)号：US08583438B2
公开(公告)日：2013-11-12
申请号：US11903020
申请日：2007-09-20
申请人： Yong Zhao , Frank Kao-ping Soong , Min Chu , Lijuan Wang
发明人： Yong Zhao , Frank Kao-ping Soong , Min Chu , Lijuan Wang
IPC分类号： G10L13/00
CPC分类号： G10L13/10
摘要： Described is a technology by which synthesized speech generated from text is evaluated against a prosody model (trained offline) to determine whether the speech will sound unnatural. If so, the speech is regenerated with modified data. The evaluation and regeneration may be iterative until deemed natural sounding. For example, text is built into a lattice that is then (e.g., Viterbi) searched to find a best path. The sections (e.g., units) of data on the path are evaluated via a prosody model. If the evaluation deems a section to correspond to unnatural prosody, that section is replaced, e.g., by modifying/pruning the lattice and re-performing the search. Replacement may be iterative until all sections pass the evaluation. Unnatural prosody detection may be biased such that during evaluation, unnatural prosody is falsely detected at a higher rate relative to a rate at which unnatural prosody is missed.

4. 发明授权

US08224652B2 Speech and text driven HMM-based body animation synthesis 有权
标题翻译：语音和文本驱动的基于HMM的身体动画综合
公开(公告)号：US08224652B2
公开(公告)日：2012-07-17
申请号：US12239564
申请日：2008-09-26
申请人： Lijuan Wang , Lei Ma , Frank Kao-Ping Soong
发明人： Lijuan Wang , Lei Ma , Frank Kao-Ping Soong
IPC分类号： G10L21/00
CPC分类号： G10L21/06 , G06T13/205 , G10L13/00
摘要： An “Animation Synthesizer” uses trainable probabilistic models, such as Hidden Markov Models (HMM), Artificial Neural Networks (ANN), etc., to provide speech and text driven body animation synthesis. Probabilistic models are trained using synchronized motion and speech inputs (e.g., live or recorded audio/video feeds) at various speech levels, such as sentences, phrases, words, phonemes, sub-phonemes, etc., depending upon the available data, and the motion type or body part being modeled. The Animation Synthesizer then uses the trainable probabilistic model for selecting animation trajectories for one or more different body parts (e.g., face, head, hands, arms, etc.) based on an arbitrary text and/or speech input. These animation trajectories are then used to synthesize a sequence of animations for digital avatars, cartoon characters, computer generated anthropomorphic persons or creatures, actual motions for physical robots, etc., that are synchronized with a speech output corresponding to the text and/or speech input.
摘要翻译： “动画合成器”采用隐马尔可夫模型（HMM），人工神经网络（ANN）等可训练概率模型，提供语音和文本驱动的人体动画合成。根据可用数据，在各种语音级别（例如句子，短语，单词，音素，子音素等）上使用同步运动和语音输入（例如，实况或记录的音频/视频馈送）训练概率模型，以及运动类型或身体部位被建模。动画合成器然后使用可训练概率模型来基于任意文本和/或语音输入来选择一个或多个不同身体部位（例如，面部，头部，手，手臂等）的动画轨迹。然后，这些动画轨迹用于合成数字化身，卡通人物，计算机生成的拟人或生物的动画序列，物理机器人的实际动作等，其与对应于文本和/或语音的语音输出同步输入。

5. 发明申请

US20120130717A1 Real-time Animation for an Expressive Avatar 审中-公开
标题翻译：表达性头像的实时动画
公开(公告)号：US20120130717A1
公开(公告)日：2012-05-24
申请号：US12950801
申请日：2010-11-19
申请人： Ning Xu , Lijuan Wang , Frank Kao-Ping Soong , Xiao Liang , Qi Luo , Ying-Qing Xu , Xin Zou
发明人： Ning Xu , Lijuan Wang , Frank Kao-Ping Soong , Xiao Liang , Qi Luo , Ying-Qing Xu , Xin Zou
IPC分类号： G10L13/00 , G06T13/00
CPC分类号： G06T13/40 , G10L2021/105 , H04L51/04 , H04L51/10 , H04L51/32
摘要： Techniques for providing real-time animation for a personalized cartoon avatar are described. In one example, a process trains one or more animated models to provide a set of probabilistic motions of one or more upper body parts based on speech and motion data. The process links one or more predetermined phrases that represent emotional states to the one or more animated models. After creation of the models, the process receives real-time speech input. Next, the process identifies an emotional state to be expressed based on the one or more predetermined phrases matching in context to the real-time speech input. The process then generates an animated sequence of motions of the one or more upper body parts by applying the one or more animated models in response to the real-time speech input.
摘要翻译：描述了为个性化卡通头像提供实时动画的技术。在一个示例中，过程训练一个或多个动画模型，以基于语音和运动数据提供一组或多个上半身部分的概率运动。该过程将表示情绪状态的一个或多个预定短语链接到一个或多个动画模型。在创建模型之后，该过程接收实时语音输入。接下来，该过程基于在上下文中与实时语音输入匹配的一个或多个预定短语来识别要表达的情绪状态。然后，该过程通过响应于实时语音输入应用一个或多个动画模型来生成一个或多个上身部分的动画序列。

6. 发明授权

US08751228B2 Minimum converted trajectory error (MCTE) audio-to-video engine 有权
标题翻译：最小转换轨迹误差（MCTE）音频到视频引擎
公开(公告)号：US08751228B2
公开(公告)日：2014-06-10
申请号：US12939528
申请日：2010-11-04
申请人： Lijuan Wang , Frank Kao-Ping Soong
发明人： Lijuan Wang , Frank Kao-Ping Soong
IPC分类号： G10L21/06
CPC分类号： G10L21/06 , G10L21/10 , G10L2021/105
摘要： Embodiments of an audio-to-video engine are disclosed. In operation, the audio-to-video engine generates facial movement (e.g., a virtual talking head) based on an input speech. The audio-to-video engine receives the input speech and recognizes the input speech as a source feature vector. The audio-to-video engine then determines a Maximum A Posterior (MAP) mixture sequence based on the source feature vector. The MAP mixture sequence may be a function of a refined Gaussian Mixture Model (GMM). The audio-to-video engine may then use the MAP to estimate video feature parameters. The video feature parameters are then interpreted as facial movement. The facial movement may be stored as data to a storage module and/or it may be displayed as video to a display device.
摘要翻译：公开了音频到视频引擎的实施例。在操作中，音频到视频引擎基于输入语音产生面部动作（例如，虚拟通话头）。音频到视频引擎接收输入语音并将输入语音识别为源特征向量。音频到视频引擎然后基于源特征向量确定最大后验（MAP）混合序列。 MAP混合序列可以是精细高斯混合模型（GMM）的函数。音频到视频引擎然后可以使用MAP估计视频特征参数。视频功能参数被解释为面部动作。面部运动可以作为数据存储到存储模块和/或其可以作为视频显示到显示装置。

7. 发明申请

US20120276504A1 Talking Teacher Visualization for Language Learning 审中-公开
标题翻译：谈话教师视觉化语言学习
公开(公告)号：US20120276504A1
公开(公告)日：2012-11-01
申请号：US13098217
申请日：2011-04-29
申请人： Gang Chen , Weijiang Xu , Lijuan Wang , Matthew Robert Scott , Frank Kao-Ping Soong , Hao Wei
发明人： Gang Chen , Weijiang Xu , Lijuan Wang , Matthew Robert Scott , Frank Kao-Ping Soong , Hao Wei
IPC分类号： G09B19/06
CPC分类号： G09B5/067 , G09B19/06
摘要： A representation of a virtual language teacher assists in language learning. The virtual language teacher may appear as a “talking head” in a video that a student views to practice pronunciation of a foreign language. A system for generating a virtual language teacher receives input text. The system may generate a video showing the virtual language teacher as a talking head having a mouth that moves in synchronization with speech generated from the input text. The video of the virtual language teacher may then be presented to the student.
摘要翻译：虚拟语言教师的代表协助语言学习。虚拟语言教师可以在学生观看练习外语的视频的视频中显示为头脑。用于生成虚拟语言教师的系统接收输入文本。该系统可以产生一个视频，显示虚拟语言教师作为一个说话人，具有与输入文本产生的语音同步移动的口。然后虚拟语言老师的视频可以呈现给学生。

8. 发明申请

US20100082345A1 SPEECH AND TEXT DRIVEN HMM-BASED BODY ANIMATION SYNTHESIS 有权
标题翻译：语音和文字驱动基于HMM的身体动画合成
公开(公告)号：US20100082345A1
公开(公告)日：2010-04-01
申请号：US12239564
申请日：2008-09-26
申请人： Lijuan Wang , Lei Ma , Frank Kao-Ping Soong
发明人： Lijuan Wang , Lei Ma , Frank Kao-Ping Soong
IPC分类号： G10L13/08 , G10L13/00 , G06T15/70
CPC分类号： G10L21/06 , G06T13/205 , G10L13/00
摘要： An “Animation Synthesizer” uses trainable probabilistic models, such as Hidden Markov Models (HMM), Artificial Neural Networks (ANN), etc., to provide speech and text driven body animation synthesis. Probabilistic models are trained using synchronized motion and speech inputs (e.g., live or recorded audio/video feeds) at various speech levels, such as sentences, phrases, words, phonemes, sub-phonemes, etc., depending upon the available data, and the motion type or body part being modeled. The Animation Synthesizer then uses the trainable probabilistic model for selecting animation trajectories for one or more different body parts (e.g., face, head, hands, arms, etc.) based on an arbitrary text and/or speech input. These animation trajectories are then used to synthesize a sequence of animations for digital avatars, cartoon characters, computer generated anthropomorphic persons or creatures, actual motions for physical robots, etc., that are synchronized with a speech output corresponding to the text and/or speech input.
摘要翻译： “动画合成器”采用隐马尔可夫模型（HMM），人工神经网络（ANN）等可训练概率模型，提供语音和文本驱动的人体动画合成。根据可用数据，在各种语音级别（例如句子，短语，单词，音素，子音素等）上使用同步运动和语音输入（例如，实况或记录的音频/视频馈送）训练概率模型，以及运动类型或身体部位被建模。动画合成器然后使用可训练概率模型来基于任意文本和/或语音输入来选择一个或多个不同身体部位（例如，面部，头部，手，手臂等）的动画轨迹。然后，这些动画轨迹用于合成数字化身，卡通人物，计算机生成的拟人或生物的动画序列，物理机器人的实际动作等，其与对应于文本和/或语音的语音输出同步输入。

9. 发明申请

US20090228273A1 HANDWRITING-BASED USER INTERFACE FOR CORRECTION OF SPEECH RECOGNITION ERRORS 审中-公开
标题翻译：用于纠正语音识别错误的基于手写的用户界面
公开(公告)号：US20090228273A1
公开(公告)日：2009-09-10
申请号：US12042344
申请日：2008-03-05
申请人： Lijuan Wang , Frank Kao-Ping Soong
发明人： Lijuan Wang , Frank Kao-Ping Soong
IPC分类号： G10L15/26 , G06F3/033 , G06K9/00
CPC分类号： G06K9/222 , G06F3/04883 , G06F17/273 , G10L15/22
摘要： A speech recognition result is displayed for review by a user. If it is incorrect, the user provides pen-based editing marks. An error type and location (within the speech recognition result) are identified based on the pen-based editing marks. An alternative result template is generated, and an N-best alternative list is also generated by applying the template to intermediate recognition results from an automatic speech recognizer. The N-best alternative list is output for use in correcting the speech recognition results.
摘要翻译：显示语音识别结果供用户查看。如果不正确，用户将提供基于笔的编辑标记。基于笔的编辑标记来识别错误类型和位置（在语音识别结果内）。生成替代结果模板，并且还通过将模板应用于自动语音识别器的中间识别结果来生成N最佳替代列表。输出N最佳替代列表以用于校正语音识别结果。

10. 发明申请

US20090083036A1 Unnatural prosody detection in speech synthesis 有权
标题翻译：语言合成中的非自然韵律检测
公开(公告)号：US20090083036A1
公开(公告)日：2009-03-26
申请号：US11903020
申请日：2007-09-20
申请人： Yong Zhao , Frank Kao-ping Soong , Min Chu , Lijuan Wang
发明人： Yong Zhao , Frank Kao-ping Soong , Min Chu , Lijuan Wang
IPC分类号： G10L13/08 , G06F17/30
CPC分类号： G10L13/10
摘要： Described is a technology by which synthesized speech generated from text is evaluated against a prosody model (trained offline) to determine whether the speech will sound unnatural. If so, the speech is regenerated with modified data. The evaluation and regeneration may be iterative until deemed natural sounding. For example, text is built into a lattice that is then (e.g., Viterbi) searched to find a best path. The sections (e.g., units) of data on the path are evaluated via a prosody model. If the evaluation deems a section to correspond to unnatural prosody, that section is replaced, e.g., by modifying/pruning the lattice and re-performing the search. Replacement may be iterative until all sections pass the evaluation. Unnatural prosody detection may be biased such that during evaluation, unnatural prosody is falsely detected at a higher rate relative to a rate at which unnatural prosody is missed.
摘要翻译：描述了一种技术，通过该技术，从文本产生的合成语音针对韵律模型（离线训练）进行评估，以确定语音是否会听起来不自然。如果是，则使用修改的数据重新生成语音。评估和再生可能是迭代的，直到被认为是自然的声音。例如，文本被内置到一个格子中，然后（例如，维特比）被搜索以找到最佳路径。通过韵律模型评估路径上的数据的部分（例如，单位）。如果评估认为一部分对应于非自然韵律，则该部分被替换，例如通过修改/修剪格子并重新执行搜索。替换可能是迭代的，直到所有部分通过评估。不自然的韵律检测可能有偏差，使得在评估期间，相对于错过非自然韵律的速率，以较高的速率错误地检测到非自然韵律。

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