公开(公告)号：US20160330557A1

公开(公告)日：2016-11-10

申请号：US15209251

申请日：2016-07-13

申请人： OtoSense Inc.

发明人： Sebastien J.V. Christian ,  Thor C. Whalen

IPC分类号： H04R29/00 ,  G08B21/18 ,  G10L25/27

CPC分类号： H04R29/00 ,  G08B17/10 ,  G08B21/0423 ,  G08B21/18 ,  G08B21/182 ,  G10H2210/031 ,  G10H2210/301 ,  G10H2240/075 ,  G10H2250/315 ,  G10L21/14 ,  G10L25/27

摘要： The disclosed embodiments provide a system that performs a sound-recognition operation. During operation, the system recognizes a sequence of sound primitives in an audio stream, wherein a sound primitive is associated with a semantic label comprising one or more words that describe a sound characterized by the sound primitive. Next, the system feeds the sequence of sound primitives into a finite-state automaton that recognizes events associated with sequences of sound primitives. Finally, the system feeds the recognized events into an output system that generates an output associated with the recognized events to be displayed to a user.

摘要翻译： 所公开的实施例提供执行声音识别操作的系统。 在操作期间，系统识别音频流中的一系列声音原语，其中声音原语与包含描述由声音原语表征的声音的一个或多个单词的语义标签相关联。 接下来，系统将声音原语的序列馈送到有限状态自动机，其识别与声音原语序列相关联的事件。 最后，系统将识别的事件馈送到输出系统中，该输出系统生成与要被显示给用户的识别事件相关联的输出。

公开(公告)号：US10198697B2

公开(公告)日：2019-02-05

申请号：US15256236

申请日：2016-09-02

申请人： OtoSense Inc.

发明人： Sebastien J. V. Christian ,  Thor C. Whalen

IPC分类号： G10L25/48 ,  G06N99/00 ,  G10L21/10 ,  G10L25/27 ,  G10L21/14 ,  G08B13/16 ,  G08B21/18

摘要： The disclosed embodiments provide a system that generates sound primitives to facilitate sound recognition. First, the system performs a feature-detection operation on sound samples to detect a set of sound features, wherein each sound feature comprises a measurable characteristic of a window of consecutive sound samples. Next, the system creates feature vectors from coefficients generated by the feature-detection operation, wherein each feature vector comprises a set of coefficients for sound features detected in a window. The system then performs a clustering operation on the feature vectors to produce feature-vector clusters, wherein each feature-vector cluster comprises a set of feature vectors that are proximate to each other in a feature-vector space that contains the feature vectors. After the clustering operation, the system defines a set of sound primitives, wherein each sound primitive is associated with a feature-vector cluster. Finally, the system associates semantic labels with the set of sound primitives.

公开(公告)号：US20180254054A1

公开(公告)日：2018-09-06

申请号：US15647798

申请日：2017-07-12

申请人： OtoSense Inc.

发明人： Thor C. Whalen ,  Sebastien J.V. Christian

IPC分类号： G10L25/27 ,  G10L25/45 ,  G10L25/51 ,  G10L21/0308 ,  G10L25/18

CPC分类号： G10L25/27 ,  G10L21/0308 ,  G10L25/18 ,  G10L25/45 ,  G10L25/51

摘要： The disclosed embodiments provide a system for recognizing a sound event in raw sound. During operation, the system receives the raw sound, wherein the raw sound comprises a sequence of digital samples of sound. Next, the system segments the raw sound into a sequence of tiles, wherein each tile comprises a set of consecutive digital samples. The system then converts the sequence of tiles into a sequence of snips, wherein each snip includes a symbol representing an associated tile in the sequence of tiles. Next, the system generates annotations for the sequence of snips and the raw sound, wherein each annotation specifies a property associated with one or more snips in the sequence of snips or the raw sound. Finally, the system recognizes the sound event based on the generated annotations.

公开(公告)号：US20180268844A1

公开(公告)日：2018-09-20

申请号：US15458412

申请日：2017-03-14

申请人： OtoSense Inc.

发明人： Thor C. Whalen ,  Sebastien J.V. Christian

IPC分类号： G10L25/51 ,  G10L25/18 ,  G10L15/18 ,  G10L21/0388

摘要： The disclosed embodiments provide a system that transforms a sound into a symbolic representation. During operation, the system extracts a sequence of tiles, comprising spectrogram slices, from the sound. Next, the system determines tile features for each tile in the sequence of tiles. The system then performs a clustering operation based on the tile features to identify clusters of tiles and to associate each tile with a cluster. Finally, the system associates each identified cluster with a unique symbol, and represents the sound as a sequence of symbols representing clusters, which are associated with the sequence of tiles.

公开(公告)号：US20160379666A1

公开(公告)日：2016-12-29

申请号：US15256236

申请日：2016-09-02

申请人： OtoSense Inc.

发明人： Sebastien J.V. Christian ,  Thor C. Whalen

IPC分类号： G10L25/48 ,  G06N99/00 ,  G10L21/10

CPC分类号： G06N99/005 ,  G08B13/1672 ,  G08B21/182 ,  G10H2210/031 ,  G10H2220/131 ,  G10H2240/075 ,  G10L21/10 ,  G10L21/14 ,  G10L25/27

摘要： The disclosed embodiments provide a system that generates sound primitives to facilitate sound recognition. First, the system performs a feature-detection operation on sound samples to detect a set of sound features, wherein each sound feature comprises a measurable characteristic of a window of consecutive sound samples. Next, the system creates feature vectors from coefficients generated by the feature-detection operation, wherein each feature vector comprises a set of coefficients for sound features detected in a window. The system then performs a clustering operation on the feature vectors to produce feature-vector clusters, wherein each feature-vector cluster comprises a set of feature vectors that are proximate to each other in a feature-vector space that contains the feature vectors. After the clustering operation, the system defines a set of sound primitives, wherein each sound primitive is associated with a feature-vector cluster. Finally, the system associates semantic labels with the set of sound primitives.

摘要翻译： 所公开的实施例提供了一种产生声音原语以促进声音识别的系统。 首先，系统对声音样本执行特征检测操作以检测一组声音特征，其中每个声音特征包括连续声音样本的窗口的可测量特性。 接下来，系统从由特征检测操作生成的系数创建特征向量，其中每个特征向量包括用于在窗口中检测到的声音特征的一组系数。 然后，系统对特征向量执行聚类操作以产生特征向量群集，其中每个特征向量群集包括在包含特征向量的特征向量空间中彼此邻近的特征向量集合。 在聚类操作之后，系统定义一组声音原语，其中每个声音原语与特征向量集群相关联。 最后，系统将语义标签与声音原语集合相关联。

公开(公告)号：US09812152B2

公开(公告)日：2017-11-07

申请号：US14616627

申请日：2015-02-06

申请人： OtoSense, Inc.

发明人： Sebastien J. V. Christian

IPC分类号： G06F17/00 ,  G10L25/27 ,  G08B21/18 ,  G08B1/08 ,  G10L25/48 ,  G10L21/14 ,  G08B17/10

CPC分类号： G10L25/27 ,  G08B1/08 ,  G08B17/10 ,  G08B21/18 ,  G10H2210/301 ,  G10L21/14 ,  G10L25/48

摘要： Systems and methods for identifying a perceived sound event are provided. In one exemplary embodiment, the system includes an audio signal receiver, a processor, and an analyzer. The system deconstructs a received audio signal into a plurality of audio chunks, for which one or more sound identification characteristics are determined. One ore more distances of a distance vector are then calculated based on one or more of the sound identification characteristics. The distance vector can be a sound gene that serves as an identifier for the sound event. The distance vector for a received audio signal is compared to distance vectors of predefined sound events to identify the source of the received audio signal. A variety of other systems and methods related to sound identification are also provided.

公开(公告)号：US09749762B2

公开(公告)日：2017-08-29

申请号：US15209251

申请日：2016-07-13

申请人： OtoSense Inc.

发明人： Sebastien J. V. Christian ,  Thor C. Whalen

IPC分类号： H04R29/00 ,  G10L25/27 ,  G08B21/18 ,  G08B17/10 ,  G10L21/14 ,  G08B21/04

CPC分类号： H04R29/00 ,  G08B17/10 ,  G08B21/0423 ,  G08B21/18 ,  G08B21/182 ,  G10H2210/031 ,  G10H2210/301 ,  G10H2240/075 ,  G10H2250/315 ,  G10L21/14 ,  G10L25/27

摘要： The disclosed embodiments provide a system that performs a sound-recognition operation. During operation, the system recognizes a sequence of sound primitives in an audio stream, wherein a sound primitive is associated with a semantic label comprising one or more words that describe a sound characterized by the sound primitive. Next, the system feeds the sequence of sound primitives into a finite-state automaton that recognizes events associated with sequences of sound primitives. Finally, the system feeds the recognized events into an output system that generates an output associated with the recognized events to be displayed to a user.

公开(公告)号：US09466316B2

公开(公告)日：2016-10-11

申请号：US14615290

申请日：2015-02-05

申请人： Otosense Inc.

发明人： Sebastien J. V. Christian

IPC分类号： G08B21/00 ,  G10L25/27 ,  G08B21/18 ,  G08B1/08 ,  G10L25/48 ,  G10L21/14 ,  G08B17/10

CPC分类号： G10L25/27 ,  G08B1/08 ,  G08B17/10 ,  G08B21/18 ,  G10H2210/301 ,  G10L21/14 ,  G10L25/48

摘要： A method, apparatus and system for transforming a progressing sound signal into a progressing visual pattern, the progressing visual pattern being perceptible and recognizable as the progressing sound signal to a user in real time. The progressing visual pattern displays in real time a set of optical attributes, the set of optical attributes being transformations from a set of sound features that define the sound signal in real time. The sound features and optical attributes, along with changes in the sound features and optical attributes over time, are preselected to be isomorphic to sound, perceptible to human vision, efficiently processed by human cognition, and therefore to be recognizable to a human who has been exposed and actively or passively trained to it.

摘要翻译： 一种用于将进行中的声音信号变换为进行中的视觉图形的方法，装置和系统，将进行中的视觉模式作为进行中的声音信号被实时感知和识别为用户。 进行的视觉图案实时地显示一组光学属性，该光学属性的集合是来自一组声音特征的实时定义声音信号的变换。 声音特征和光学属性以及随时间的声音特征和光学属性的变化被预先选择为与人类视觉可察觉的声音同构，由人类认知有效地处理，并且因此被识别为已经被人 暴露并积极或被动地训练它。