Capture interspeaker information with a neural network for speaker identification

Model-based approach is one of methods widely used for speaker identification, where a statistical model is used to characterize a specific speaker's voice but no interspeaker information is involved in its parameter estimation. It is observed that interspeaker information is very helpful in discriminating between different speakers. In this paper, we propose a novel method for the use of interspeaker information to improve performance of a model-based speaker identification system. A neural network is employed to capture the interspeaker information from the output space of those statistical models. In order to sufficiently utilize interspeaker information, a rival penalized encoding rule is proposed to design supervised learning pairs. For better generalization, moreover, a query-based learning algorithm is presented to actively select the input data of interest during training of the neural network. Comparative results on the KING speech corpus show that our method leads to a considerable improvement for a model-based speaker identification system.

I. Introduction

THE goal of speaker identification is to automatically determine a speaker's identity by his/her voice among a population. It is widely applied to many fields from confidential data access to audio indexing in multimedia [14]. In general, a speaker identification system may be either text-dependent, where the same text is required for both training and test, or text-independent, where arbitrary text is allowed to utter.