Effective estimation of a multi-session speaker model using information on signal parameters
نویسندگان
چکیده
The paper deals with the problem of estimation an optimal ivector based speaker voice model using several sessions of his or her voice recordings, each of which has different signal parameters: speech duration and SNR. Our aim is to minimize inter-session variability so as to achieve minimal EER in the task of speaker recognition. We examine the influence of the main signal parameters on inter-session variability and propose a model for multi-session ivector estimation based on minimizing inter-session variability.
منابع مشابه
Estimation of harmonic interference parameters of surface-NMR signal using an adaptive method and residual signal power
Surface nuclear magnetic resonance (surface-NMR) method is a well-known tool for determining the water-bearing layers and subsurface resistivity structure. Harmonic interference is an inevitable interference in surface-NMR measurements. Accurate estimation of harmonic interference parameters (i.e., fundamental frequency, phase and amplitude) leads to better retrieval of power-line harmonics and...
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 کاملشبکه عصبی پیچشی با پنجرههای قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کاملDeveloping 3 dimensional model for estimation of acoustic power in urban pathways in geo-spatial information system framework
Around the word, traffic growth is causing growing air and noise pollution. Noise levels in a given area are affected by traffic on the streets as well as effective factors, including existing infrastructure and industrial centers, and so on. The purpose of this research is to model and estimate the amount of acoustic emission in the streets of Tehran's third district, using the 3D spatial info...
متن کامل