公开(公告)号：US20100138010A1

公开(公告)日：2010-06-03

申请号：US12349496

申请日：2009-01-06

申请人： Si Mohamed Aziz Sbai ,  Raphael Blouet ,  Antoine Liutkus

发明人： Si Mohamed Aziz Sbai ,  Raphael Blouet ,  Antoine Liutkus

IPC分类号： G06F17/00

CPC分类号： G10H1/0008 ,  G10H2210/031 ,  G10L21/028

摘要： Unsupervised learning algorithms for audio source separation such as non-negative matrix factorization (NMF) and principal components analysis (PCA) can be understood as a data matrix factorization subject to different constraints. These algorithms provide components with a relevant structure and homogeneous musical events. The invention presents an automatic fusion method to merge these components into tracks associated to the different instruments present in the sound source.

摘要翻译： 用于音频源分离的无监督学习算法，如非负矩阵分解（NMF）和主成分分析（PCA）可以被理解为受不同约束条件的数据矩阵分解。 这些算法为组件提供了相关的结构和均匀的音乐事件。 本发明提供了一种将这些组件合并成与声源中存在的不同仪器相关联的轨道的自动融合方法。

公开(公告)号：US20100174389A1

公开(公告)日：2010-07-08

申请号：US12349494

申请日：2009-01-06

申请人： Raphael Blouet ,  Si Mohamed Aziz Sbai ,  Antoine Liutkus

发明人： Raphael Blouet ,  Si Mohamed Aziz Sbai ,  Antoine Liutkus

IPC分类号： G06F17/00 ,  G06N5/02

CPC分类号： G10L21/028

摘要： A method is provided that comprises segmenting an audio source file; optimizing a model based upon probability; and separating the audio source file.

摘要翻译： 提供一种包括分割音频源文件的方法; 基于概率优化模型; 并分离音频源文件。

公开(公告)号：US09646613B2

公开(公告)日：2017-05-09

申请号：US14093200

申请日：2013-11-29

申请人： Raphael Blouet

发明人： Raphael Blouet

IPC分类号： G10L21/00 ,  G10L17/22 ,  G10L15/04 ,  G10L17/04 ,  G10L17/16 ,  G10L15/18 ,  H04M3/38

CPC分类号： G10L17/22 ,  G10L15/04 ,  G10L15/1807 ,  G10L17/04 ,  G10L17/16 ,  H04M3/385

摘要： A method for splitting a digital signal using prosodic features included in the signal is provided that includes calculating onset value locations in the signal. The onset values correspond to stress accents in the signal. Moreover, the method includes splitting, using a processor, the signal into a prosodic unit candidate sequence by superimposing the stress accent locations on the signal, and processing the sequence to include only true prosodic units.

公开(公告)号：US20110194709A1

公开(公告)日：2011-08-11

申请号：US13021692

申请日：2011-02-04

申请人： Alexey Ozerov ,  Raphael Blouet ,  Cédric Févotte

发明人： Alexey Ozerov ,  Raphael Blouet ,  Cédric Févotte

IPC分类号： H04B1/00

CPC分类号： G10L21/0272 ,  G10L25/18

摘要： A source separation system is provided. The system includes a plurality of sources being subjected to an automatic source separation via a joint use of segmental information and spatial diversity. The system further includes a set of spectral shapes representing spectral diversity derived from the automatic source separation being automatically provided. The system still further includes a plurality of mixing parameters derived from the set of spectral shapes. Within a sampling range, a triplet is processed wherein a reconstruction of a Short Term Fourier Transform (STFT) corresponding to a source triplet among the set of triplets is performed.

摘要翻译： 提供源分离系统。 该系统包括通过联合使用分段信息和空间分集而经受自动源分离的多个源。 该系统还包括一组频谱形状，表示自动提供自动源分离所得到的频谱分集。 该系统还包括从该组光谱形状导出的多个混合参数。 在采样范围内，处理三重态，其中执行对应于该组三元组中的源三元组的短期傅里叶变换（STFT）的重构。

公开(公告)号：US10083696B1

公开(公告)日：2018-09-25

申请号：US15451460

申请日：2017-03-07

申请人： Raphael Blouet

发明人： Raphael Blouet

IPC分类号： G10L17/00 ,  G10L17/08 ,  G10L17/22 ,  G10L17/26

摘要： A method for determining user liveness is provided that includes calculating, by a computing device, a spectral property difference between voice biometric data captured from a user and user record voice biometric data. The user and the computing device constitute a user-computing device pair, and the voice biometric data is captured by the computing device during a verification transaction. Moreover, the method includes inputting the spectral property difference into a machine learning algorithm, calculating an output score with the machine learning algorithm, and determining the voice biometric data was captured from a live user when the output score satisfies a threshold score.