End-to-end speaker recognition using deep neural network
AssigneePindrop Security, Inc.
InventorsElie Khoury, Matthew Garland
Life of this patent
Estimating the term…
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.
Claims14
A speaker recognition device including a processor-based device having been configured to model a trained deep neural network with a triplet network architecture, the deep neural network having been trained according to a process in which dual sets of speech samples are fed through the deep neural network in combination with a cohort set of speech samples not attributed to the same speaker as the dual sets, comprising:
- a memory device storing speech samples including a set of speaker models;
- and
- the processor-based device feeding a recognition speech sample through the trained deep neural network, and verifying or identifying a user based on an output of the trained deep neural network responsive to the recognition speech sample and at least one of the speaker models.
A method of using a speaker recognition device including a processor-based device having been configured to model a trained deep neural network with a triplet network architecture, the deep neural network having been trained according to a process in which dual sets of speech samples are fed through the deep neural network in combination with a cohort set of speech samples not attributed to the same speaker as the dual sets, the method comprising:
- storing speech samples including a set of speaker models;
- and
- feeding a recognition speech sample through the trained deep neural network, and verifying or identifying a user based on an output of the trained deep neural network responsive to the recognition speech sample and at least one of the speaker models.
Dependencies are inferred from the claim text.