公开(公告)号：US20140195232A1

公开(公告)日：2014-07-10

申请号：US13854134

申请日：2013-04-01

Applicant: STMicroelectronics Asia Pacific Pte Ltd.

Inventor： Evelyn Kurniawati ,  Sapna George

IPC: G10L17/04

CPC classification number: G10L17/04 ,  G10L15/063 ,  G10L15/144 ,  G10L17/02 ,  G10L17/06

Abstract: Embodiments provide a method and system of text independent speaker recognition with a complexity comparable to a text dependent version. The scheme exploits the fact that speech is a quasi-stationary signal and simplifies the recognition process based on this theory. The modeling allows the speaker profile to be updated progressively with the new speech sample that is acquired during usage time.

Abstract translation: 实施例提供了具有与文本相关版本相当的复杂性的文本独立说话人识别的方法和系统。 该方案利用了语音是准稳态信号，并简化了基于该理论的识别过程。 该建模允许使用在使用时间期间获取的新的语音样本来逐渐更新扬声器简档。

公开(公告)号：US09530417B2

公开(公告)日：2016-12-27

申请号：US13854134

申请日：2013-04-01

Applicant: STMicroelectronics Asia Pacific Pte Ltd.

Inventor： Evelyn Kurniawati ,  Sapna George

IPC: G10L17/02 ,  G10L17/04 ,  G10L15/06 ,  G10L15/14 ,  G10L17/06

CPC classification number: G10L17/04 ,  G10L15/063 ,  G10L15/144 ,  G10L17/02 ,  G10L17/06

Abstract: Methods and systems of text independent speaker recognition provide a complexity comparable to text dependent speaker recognition system. These methods and systems exploit the fact that speech is a quasi-stationary signal and simplify the recognition process based on this theory. The speaker modeling allows a speaker profile to be updated progressively with new speech samples that are acquired during usage over time by the speaker.

Abstract translation: 文本独立说话人识别的方法和系统提供了与文本相关的扬声器识别系统相当的复杂性。 这些方法和系统利用语音是准稳态信号，并且基于这个理论简化识别过程。 扬声器建模允许使用由扬声器随着时间的使用获取的新语音样本来逐渐更新扬声器简档。

公开(公告)号：US09633652B2

公开(公告)日：2017-04-25

申请号：US13854133

申请日：2013-03-31

Applicant: STMicroelectronics Asia Pacific Pte Ltd.

Inventor： Evelyn Kurniawati ,  Sapna George

IPC: G10L15/07 ,  G10L15/14 ,  G10L17/04 ,  G10L15/00 ,  G10L15/06

CPC classification number: G10L15/144 ,  G10L15/00 ,  G10L15/06 ,  G10L15/07 ,  G10L17/04

Abstract: Embodiments reduce the complexity of speaker dependent speech recognition systems and methods by representing the code phrase (i.e., the word or words to be recognized) using a single Gaussian Mixture Model (GMM) which is adapted from a Universal Background Model (UBM). Only the parameters of the GMM need to be stored. Further reduction in computation is achieved by only checking the GMM component that is relevant to the keyword template. In this scheme, keyword template is represented by a sequence of the index of best performing component of the GMM of the keyword model. Only one template is saved by combining the registration template using Longest Common Sequence algorithm. The quality of the word model is continuously updated by performing expectation maximization iteration using the test word which is accepted as keyword model.

公开(公告)号：US20140200890A1

公开(公告)日：2014-07-17

申请号：US13854133

申请日：2013-03-31

Applicant: STMicroelectronics Asia Pacific Pte Ltd.

Inventor： Evelyn Kurniawati ,  Sapna George

IPC: G10L15/14

CPC classification number: G10L15/144 ,  G10L15/00 ,  G10L15/06 ,  G10L15/07 ,  G10L17/04

Abstract: Embodiments reduce the complexity of speaker dependent speech recognition systems and methods by representing the code word (i.e., the word to be recognized) using a single Gaussian Mixture Model (GMM) which is adapted from a Universal Background Model (UBM). Only the parameters of the GMM need to be stored. Further reduction in computation is achieved by only checking the GMM component that is relevant to the keyword template. In this scheme, keyword template is represented by a sequence of the index of best performing component of the GMM of the keyword model. Only one template is saved by combining the registration template using Longest Common Sequence algorithm. The quality of the word model is continuously updated by performing expectation maximization iteration using the test word which is accepted as keyword model.

Abstract translation: 实施例通过使用从通用背景模型（UBM）改编的单个高斯混合模型（GMM）来表示代码字（即，要识别的单词）来降低说话者依赖语音识别系统和方法的复杂性。 只需要存储GMM的参数。 仅通过检查与关键字模板相关的GMM组件来实现计算的进一步减少。 在该方案中，关键字模板由关键字模型的GMM的最佳执行组件的索引的序列表示。 通过使用最长公共序列算法组合注册模板，仅保存一个模板。 通过使用被接受为关键字模型的测试词来执行期望最大化迭代，不断更新单词模型的质量。