公开(公告)号：US10325601B2

公开(公告)日：2019-06-18

申请号：US15709290

申请日：2017-09-19

Applicant: PINDROP SECURITY, INC.

Inventor： Elie Khoury ,  Matthew Garland

IPC: G10L17/00 ,  G06N7/00 ,  G10L15/07 ,  G10L15/26 ,  G10L17/04 ,  H04M1/27 ,  G10L17/24 ,  G10L15/19 ,  G10L17/08

Abstract: Utterances of at least two speakers in a speech signal may be distinguished and the associated speaker identified by use of diarization together with automatic speech recognition of identifying words and phrases commonly in the speech signal. The diarization process clusters turns of the conversation while recognized special form phrases and entity names identify the speakers. A trained probabilistic model deduces which entity name(s) correspond to the clusters.

公开(公告)号：US09824692B1

公开(公告)日：2017-11-21

申请号：US15262748

申请日：2016-09-12

Applicant: PINDROP SECURITY, INC.

Inventor： Elie Khoury ,  Matthew Garland

IPC: G10L17/18 ,  G10L15/16 ,  G10L17/04 ,  G10L17/08 ,  G10L17/02 ,  G10L17/22 ,  G06N3/04 ,  G06N3/08

CPC classification number: G10L17/08 ,  G06N3/04 ,  G06N3/08 ,  G10L15/16 ,  G10L17/02 ,  G10L17/04 ,  G10L17/18 ,  G10L17/22

Abstract: The present invention is directed to a deep neural network (DNN) having a triplet network architecture, which is suitable to perform speaker recognition. In particular, the DNN includes three feed-forward neural networks, which are trained according to a batch process utilizing a cohort set of negative training samples. After each batch of training samples is processed, the DNN may be trained according to a loss function, e.g., utilizing a cosine measure of similarity between respective samples, along with positive and negative margins, to provide a robust representation of voiceprints.