Improvements in the speaker identification rate using feature-sets
نویسندگان
چکیده
In this paper we look at the parameterized feature-set that has been used in connected alpha-digit speech recognition and evaluate it on a speaker identification SID system. Compared to the popular mel-scaled featureset (MFCC) the parameterized feature-set gives over 21% improvement in identification rate on the NTIMIT database in some cases. On average it has a 14.0% improvement. This demonstrates how feature-sets can be used to improve the performance of speaker identification systems.
منابع مشابه
Improvements in the speaker identification rate using feature-sets on a large population database
In this paper we look at the parameterized feature-set that has been used in connected alpha-digit speech recognition and evaluate it on a speaker identification SID system. Compared to the popular mel-scaled featureset (MFCC) the parameterized feature-set gives over 21% improvement in identification rate on the NTIMIT database in some cases. On average it has a 14.0% improvement. This demonstr...
متن کاملRobust Text Independent Speaker Identification Using Hybrid GMM-SVM System
This paper introduces and motivates the use of the statistical method Gaussian Mixture Model (GMM) and Support Vector Machines (SVM) for robust textindependent speaker identification. Features are extracted from the dialect DR1 of the Timit corpus. They are presented by MFCC, energy, Delta and Delta-Delta coefficients. GMM is used to model the feature extractor of the input speech signal and SV...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملA Multi Level Data Fusion Approach for Speaker Identification on Telephone Speech
Several speaker identification systems are giving good performance with clean speech but are affected by the degradations introduced by noisy audio conditions. To deal with this problem, we investigate the use of complementary information at different levels for computing a combined match score for the unknown speaker. In this work, we observe the effect of two supervised machine learning appro...
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 2001