公开(公告)号：EP3198247A1

公开(公告)日：2017-08-02

申请号：EP15844354.9

申请日：2015-09-25

申请人： Sunhouse Technologies, Inc.

发明人： ESPARZA, Tlacaelel Miguel

IPC分类号： G01H11/08

CPC分类号： G10H3/146 ,  G01H1/00 ,  G01H11/00 ,  G01H11/02 ,  G01H11/08 ,  G10D13/024 ,  G10H1/14 ,  G10H3/12 ,  G10H3/143 ,  G10H7/008 ,  G10H2210/041 ,  G10H2210/051 ,  G10H2210/281 ,  G10H2220/091 ,  G10H2220/525 ,  G10H2230/281 ,  G10H2250/235 ,  G10H2250/311 ,  G10H2250/435 ,  G10H2250/641

摘要： As part of a system, a device is provided as part of a system, the device being for capturing vibrations produced by an object such as a musical instrument. The device has a first sensor placed in contact with a surface of the drum, such as a rim of the drum, and a second sensor placed at a fixed location relative to the drum, but not touching the drum. A method may be provided for interpreting the output of the sensors within the system, the method comprising identifying the onset of an audio event in audio data, selecting a window in the data for analysis, applying transforms to generate a representation of the audio event, and comparing that representation to expected representations in a model.

摘要翻译： 设备被提供作为系统的一部分，该设备用于捕捉由诸如乐器的物体产生的振动。 该装置通过固定元件固定在鼓上。 该装置具有与相对于鼓定位的鼓的表面间隔开的传感器以及与传感器相邻的磁体。 固定元件将振动从鼓上的固定点传递到磁体。 鼓表面和磁铁表面的振动传递到传感器。 可以进一步提供用于解释音频输入（例如系统内的传感器的输出）的方法，该方法包括识别音频事件或音频数据内的音频事件的分组，生成音频事件的模型，该模型包括表示 音色特征，并将该表示与预期表示进行比较。

公开(公告)号：EP4070050A1

公开(公告)日：2022-10-12

申请号：EP20896351.2

申请日：2020-12-01

申请人： Sunhouse Technologies, Inc.

发明人： ESPARZA, Tlacaelel, Miguel

IPC分类号： G01H11/06 ,  G10D13/063 ,  G10H3/14

公开(公告)号：EP3889954A1

公开(公告)日：2021-10-06

申请号：EP21162445.7

申请日：2015-09-25

申请人： Sunhouse Technologies, Inc.

发明人： ESPARZA, Tlacaelel Miguel

IPC分类号： G10H1/06 ,  G10H7/00 ,  G10H3/12

摘要： A method for extracting audio from electrical signals within a data processing device comprises
- receiving, at the data processing device, a stream of audio input data;
- identifying, in the audio input data, at least one audio event;
- generating, by the data processing device, an n-dimensional representation of the audio event; and
- classifying the audio event by comparing at least one dimension of the representation of the audio event to a corresponding dimension of expected representations of a plurality of audio events.