公开(公告)号：US20160063991A1

公开(公告)日：2016-03-03

申请号：US14936772

申请日：2015-11-10

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

Inventor： Sumit CHOPRA ,  Dimitrios DIMITRIADIS ,  Patrick HAFFNER

IPC: G10L15/02 ,  G10L15/08

CPC classification number: G10L15/02 ,  G10L15/08 ,  G10L15/16

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations. Based on the scores, the plurality of segmental classification units selects a class label and returns a result.

公开(公告)号：US20150058012A1

公开(公告)日：2015-02-26

申请号：US14537400

申请日：2014-11-10

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

Inventor： Sumit CHOPRA ,  Dimitrios DIMITRIADIS ,  Patrick HAFFNER

IPC: G10L15/08

CPC classification number: G10L15/02 ,  G10L15/08 ,  G10L15/16

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations. Based on the scores, the plurality of segmental classification units selects a class label and returns a result.

Abstract translation: 本文公开了用于通过时间池来组合帧和段级处理用于语音分类的系统，方法和非暂时的计算机可读存储介质。 帧处理器单元接收输入并从输入中提取与时间相关的特征。 多个池化接口单元基于集合时间依赖特征并根据多个选择策略选择多个时间相关特征来生成多个特征向量。 接下来，多个分段分类单元生成特征向量的得分。 每个分段分类单元（SCU）可专用于特定的汇聚接口单元（PIU）以形成PIU-SCU组合。 可以进一步组合多个PIU-SCU组合以形成组合的集合，并且可以通过改变PIU-SCU组合使用的合并操作来使集合多样化。 基于分数，多个分段分类单元选择分类标签并返回结果。

公开(公告)号：US20150081302A1

公开(公告)日：2015-03-19

申请号：US14551907

申请日：2014-11-24

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

Inventor： Ann K. SYRDAL ,  Sumit CHOPRA ,  Patrick Haffner ,  Taniya MISHRA ,  Ilija ZELJKOVIC ,  Eric Zavesky

IPC: G10L17/24

CPC classification number: G10L15/25 ,  G06F21/32 ,  G06F2221/2103 ,  G06K9/00255 ,  G06K9/00281 ,  G06K9/00288 ,  G06K9/00315 ,  G06K9/00335 ,  G10L17/24 ,  G10L21/06

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing speaker verification. A system configured to practice the method receives a request to verify a speaker, generates a text challenge that is unique to the request, and, in response to the request, prompts the speaker to utter the text challenge. Then the system records a dynamic image feature of the speaker as the speaker utters the text challenge, and performs speaker verification based on the dynamic image feature and the text challenge. Recording the dynamic image feature of the speaker can include recording video of the speaker while speaking the text challenge. The dynamic feature can include a movement pattern of head, lips, mouth, eyes, and/or eyebrows of the speaker. The dynamic image feature can relate to phonetic content of the speaker speaking the challenge, speech prosody, and the speaker's facial expression responding to content of the challenge.

Abstract translation: 本文公开了用于执行说话者验证的系统，方法和非暂时的计算机可读存储介质。 被配置为实施该方法的系统接收到验证说话者的请求，产生对该请求是唯一的文本挑战，并且响应该请求提示说话者发出文本挑战。 然后当扬声器发出文本挑战时，系统记录扬声器的动态图像特征，并且基于动态图像特征和文本挑战来执行说话者验证。 录制扬声器的动态图像功能可以包括在说出文本挑战时录制扬声器的视频。 动态特征可以包括扬声器的头部，嘴唇，嘴巴，眼睛和/或眉毛的运动模式。 动态图像特征可以涉及讲话者讲话的语音内容，语音韵律以及响应于挑战内容的说话者的面部表情。

公开(公告)号：US20160078869A1

公开(公告)日：2016-03-17

申请号：US14953984

申请日：2015-11-30

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

Inventor： Ann K. SYRDAL ,  Sumit CHOPRA ,  Patrick HAFFNER ,  Taniya MISHRA ,  Ilija ZELJKOVIC ,  Eric ZAVESKY

IPC: G10L15/25 ,  G06K9/00 ,  G10L21/06

CPC classification number: G10L15/25 ,  G06F21/32 ,  G06F2221/2103 ,  G06K9/00255 ,  G06K9/00281 ,  G06K9/00288 ,  G06K9/00315 ,  G06K9/00335 ,  G10L17/24 ,  G10L21/06

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing speaker verification. A system configured to practice the method receives a request to verify a speaker, generates a text challenge that is unique to the request, and, in response to the request, prompts the speaker to utter the text challenge. Then the system records a dynamic image feature of the speaker as the speaker utters the text challenge, and performs speaker verification based on the dynamic image feature and the text challenge. Recording the dynamic image feature of the speaker can include recording video of the speaker while speaking the text challenge. The dynamic feature can include a movement pattern of head, lips, mouth, eyes, and/or eyebrows of the speaker. The dynamic image feature can relate to phonetic content of the speaker speaking the challenge, speech prosody, and the speaker's facial expression responding to content of the challenge.