A new classifier is presented for text-independent speaker recognition. The new classifier is called the modified neural tree network (MNTN). The NTN is a hierarchical classifier that combines the properties of decision trees and feed-forward neural networks. The MNTN differs from the stan(cid:173) dard NTN in that a new learning rule based on discriminant learning is used, which minimizes the classification error as opposed to a norm of the approximation error. The MNTN also uses leaf probability mea(cid:173) sures in addition to the class labels.

At MNTN, we've built a culture based on quality, trust, ambition, and accountability – but most importantly, we really enjoy working here. We pride ourselves on our self-service platform, originally coded by our President and CEO, and are constantly seeking to improve the user experience for our customers and scale for efficiency. Our startup spirit powers our growth mindset and supports our teammates as they build the future of ConnectedTV. We're looking for people who naturally want to do more, own more, and make an impact in their careers – and we're seeking someone to be part of our next stage of growth. As a Lead Data Scientist on our Targeting team, you will guide the analysis, methodologies, prototypes and evolution of our audience targeting system.

At MNTN, we've built a culture based on quality, trust, ambition, and accountability – but most importantly, we really enjoy working here. We pride ourselves on our self-service platform, originally coded by our President and CEO, and are constantly seeking to improve the user experience for our customers and scale for efficiency. Our startup spirit powers our growth mindset and supports our teammates as they build the future of ConnectedTV. We're looking for people who naturally want to do more, own more, and make an impact in their careers – and we're seeking someone to be part of our next stage of growth. As a Machine Learning Engineer on our Attribution team, you will ideate, train, test, deploy, evaluate and monitor matching systems in a large scale production environment to maximize advertiser goals while respecting consumer privacy.

A new classifier is presented for text-independent speaker recognition. The new classifier is called the modified neural tree network (MNTN). The NTN is a hierarchical classifier that combines the properties of decision trees and feed-forward neural networks. The MNTN differs from the standard NTN in that a new learning rule based on discriminant learning is used, which minimizes the classification error as opposed to a norm of the approximation error. The MNTN also uses leaf probability measures in addition to the class labels.

A new classifier is presented for text-independent speaker recognition. The new classifier is called the modified neural tree network (MNTN). The NTN is a hierarchical classifier that combines the properties of decision trees and feed-forward neural networks. The MNTN differs from the standard NTN in that a new learning rule based on discriminant learning is used, which minimizes the classification error as opposed to a norm of the approximation error. The MNTN also uses leaf probability measures in addition to the class labels.

A new classifier is presented for text-independent speaker recognition. The new classifier is called the modified neural tree network (MNTN). The NTN is a hierarchical classifier that combines the properties of decision trees and feed-forward neural networks. The MNTN differs from the standard NTNin that a new learning rule based on discriminant learning is used, which minimizes the classification error as opposed to a norm of the approximation error. The MNTN also uses leaf probability measures inaddition to the class labels.