Analysis of i-vector Length Normalization in Speaker Recognition Systems
نویسندگان
چکیده
We present a method to boost the performance of probabilistic generative models that work with i-vector representations. The proposed approach deals with the nonGaussian behavior of i-vectors by performing a simple length normalization. This non-linear transformation allows the use of probabilistic models with Gaussian assumptions that yield equivalent performance to that of more complicated systems based on Heavy-Tailed assumptions. Significant performance improvements are demonstrated on the telephone portion of NIST SRE 2010.
منابع مشابه
Variance-spectra based normalization for i-vector standard and probabilistic linear discriminant analysis
I-vector extraction and Probabilistic Linear Discriminant Analysis (PLDA) has become the state-of-the-art configuration for speaker verification. Recently, Gaussian-PLDA has been improved by a preliminary length normalization of i-vectors. This normalization, known to increase the Gaussianity of the i-vector distribution, also improves performance of systems based on standard Linear Discriminan...
متن کاملI–vector transformation and scaling for PLDA based speaker recognition
This paper proposes a density model transformation for speaker recognition systems based on i–vectors and Probabilistic Linear Discriminant Analysis (PLDA) classification. The PLDA model assumes that the i-vectors are distributed according to the standard normal distribution, whereas it is well known that this is not the case. Experiments have shown that the i–vector are better modeled, for exa...
متن کاملEvaluation of i-vector Speaker Recognition Systems for Forensic Application
This paper contributes a study on i-vector based speaker recognition systems and their application to forensics. The sensitivity of i-vector based speaker recognition is analyzed with respect to the effects of speech duration. This approach is motivated by the potentially limited speech available in a recording for a forensic case. In this context, the classification performance and calibration...
متن کاملAnalysis of mutual duration and noise effects in speaker recognition: benefits of condition-matched cohort selection in score normalization
The biometric and forensic performance of automatic speaker recognition systems degrades under noisy and short probe utterance conditions. Score normalization is an effective tool taking into account the mismatch of reference and probe utterances. In an adaptive symmetric score normalization scheme for state-ofthe-art i-vector recognition systems, a set of cohort speakers are employed to calcul...
متن کاملEffect of multicondition training on i-vector PLDA configurations for speaker recognition
The i-vector representation and PLDA classifier have shown state-of-the-art performance for speaker recognition systems. The availability of more than one enrollment utterance for a speaker allows a variety of configurations which can be used to enhance robustness to noise. The well-known technique of multicondition training can be utilized at different stages of the system, including enrollmen...
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 2011