We explore an approach to speaker identification called speaker clustering in the GMM-
based speaker recognition system in order to reduce the computational complexity. The …

The issue of input variability resulting from speaker changes is one of the most crucial
factors influencing the effectiveness of speech recognition systems. A solution to this …

识别正确率和抗噪性能固然是说话人识别的研究重点, 但识别响应速度也是决定系统实用化的
关键所在. 本文成功地提出了基于说话人分类技术的分级说话人辨识方法 …

In the context of the Neologos French speech database creation project, a general
methodology was defined for the selection of representative speaker recordings. The …

This paper addresses the estimation of a speaker GMM through the selection and merging
of a set of neighbors models for that speaker. The selection of the neighbors models is …

Esta tesis se enmarca dentro de dos proyectos, uno ya finalizado, denominado BASURDE
(Bonafonte et~ al., 2000), y otro en curso, denominado DIHANA (DIHANA, 2003-2005), que …

Abstract In previous work [1], it was investigated how the neighborhood can be used to
estimate a better model for a speaker when few training data is avalaible. In this paper, this …

Feature space Maximum Likelihood Linear Regression (fMLLR) is known as an effective
algorithm for rapid speaker adaptation to a new speaker or environment. In this paper we …

Given a piece of audio recording, the task of speaker diarization can be summarized as
answering the question of “Who spoke when?”. This thesis offers a review of the techniques …

Advances in mobile computer systems, signal processing and sensing technology enable
new computing applications to support the user anywhere and anytime. One such …