Analysis of Feature Extraction and Channel Compensation in a GMM Speaker Recognition System
نویسندگان
چکیده
منابع مشابه
Channel compensation for SVM speaker recognition
One of the major remaining challenges to improving accuracy in state-of-the-art speaker recognition algorithms is reducing the impact of channel and handset variations on system performance. For Gaussian Mixture Model based speaker recognition systems, a variety of channel-adaptation techniques are known and available for adapting models between different channel conditions, but for the much mo...
متن کاملChannel Compensation for Speaker Recognition Systems
..............................................................................................................IV PUBLICATIONS ......................................................................................................VI TABLE OF CONTENTS........................................................................................ VII LIST OF FIGURES............................................
متن کاملa contrastive analysis of concord and head parameter in english and azerbaijani
این پایان نامه به بررسی و مقایسه دو موضوع مطابقه میان فعل و فاعل (از نظر شخص و مشار) و هسته عبارت در دو زبان انگلیسی و آذربایجانی می پردازد. اول رابطه دستوری مطابقه مورد بررسی قرار می گیرد. مطابقه به این معناست که فعل مفرد به همراه فاعل مفرد و فعل جمع به همراه فاعل جمع می آید. در انگلیسی تمام افعال، بجز فعل بودن (to be) از نظر شمار با فاعلشان فقط در سوم شخص مفرد و در زمان حال مطابقت نشان میدهند...
15 صفحه اولOptimisation of GMM in speaker recognition
Given that the amount of speaker speci c training data is always limited, for a given amount of data a speaker model has an optimum number of components. Here, this is investigated with regard to Gaussian mixture models (GMM) with and without world model adaption. Test results show that maximising the number of components in a speaker model can improve speaker recognition results. Comparisons w...
متن کاملEfficient Training of GMM Based Speaker Recognition System
Automatic speaker recognition (ASR) is based on speech feature vectors, models, and classifiers. To improve the speaker recognition performance, we must affect at least one of these modules. In this paper we propose to use subband spectral centroids (SSCs) as a complementary features with the traditional MFCC features, and a new GMM training algorithm, with the ultimate goal to search the bette...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Audio, Speech, and Language Processing
سال: 2007
ISSN: 1558-7916,1558-7924
DOI: 10.1109/tasl.2007.902499