Data-driven clustering for blind feature mapping in speaker verification
نویسندگان
چکیده
Handset and channel mismatch degrades the performance of automatic speaker recognition systems significantly. This paper enhances the feature mapping technique by proposing an iterative clustering approach to context model generation which offers an improvement in the performance of feature mapping trained on labelled data and offers the potential to train feature mapping in the absence of correctly labelled background data. The performance of the clustered feature mapping models is demonstrated on an expanded version of the NIST 2003 Extended Data Task (EDT) protocol.
منابع مشابه
A clustering approach for mineral potential mapping: A deposit-scale porphyry copper exploration targeting
This work describes a knowledge-guided clustering approach for mineral potential mapping (MPM), by which the optimum number of clusters is derived form a knowledge-driven methodology through a concentration-area (C-A) multifractal analysis. To implement the proposed approach, a case study at the North Narbaghi region in the Saveh, Markazi province of Iran, was investigated to discover porphyry ...
متن کاملProbabilistic feature-based transformation for speaker verification over telephone networks
Feature transformation aims to reduce the effects of channeland handset-distortion in telephone-based speaker verification. This paper compares several feature transformation techniques and evaluates their verification performance and computation time under the 2000 NIST speaker recognition evaluation protocol. Techniques compared include feature mapping (FM), stochastic feature transformation ...
متن کاملSpeech-Singing Discrimination using Geometric Methods
Automatic audio classification is a growing area of interest applicable to media services, search engines and intelligent human-computer systems. Human utterance classification is a subset of audio signals classification. Tasks such as speaker verification and speech recognition are an old problem. But human utterance also includes singing, shouting and other forms involving human voice. Classi...
متن کاملEfficient text-independent speaker verification with structural Gaussian mixture models and neural network
We present an integrated system with structural Gaussian mixture models (SGMMs) and a neural network for purposes of achieving both computational efficiency and high accuracy in text-independent speaker verification. A structural background model (SBM) is constructed first by hierarchically clustering all Gaussian mixture components in a universal background model (UBM). In this way the acousti...
متن کاملBiologically inspired speaker verification
Speaker verification is an active research problem that has been addressed using a variety of different classification techniques. However, in general, methods inspired by the human auditory system tend to show better verification performance than other methods. In this thesis three biologically inspired speaker verification algorithms are presented. The first is a vowel-dependent speaker verif...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005