Independent components for acoustic modeling
نویسندگان
چکیده
In the paper, we present a comparative study of several methods used nowadays in the field of feature and information extraction. We compared several Independent Component Analysis (ICA) algorithms together with the commonly used Principal Component Analysis (PCA) algorithm in two real-world tasks. The first task was a Voice Activity Detection (VAD), the second is Speaker Verification and Recognition (SVR). The VAD system as well as the SVR system benefited from the ICA decompositions. Moreover, a brief comparison of the information extraction ability is described.
منابع مشابه
Modeling and simulation of the acoustic behavior of a muffler in a passenger car exhaust system
Muffler is one of the main components of an automotive exhaust system, which reduces the noise of the exhaust system. In this paper, modeling and simulation of the acoustic behavior of a muffler is presented with the aid of an engineering software. For this purpose, firstly, an analytical model is presented to evaluate the sound transmission loss in cylindrical shells based on Sander's theory....
متن کاملA High Order Approximation of the Two Dimensional Acoustic Wave Equation with Discontinuous Coefficients
This paper concerns with the modeling and construction of a fifth order method for two dimensional acoustic wave equation in heterogenous media. The method is based on a standard discretization of the problem on smooth regions and a nonstandard method for nonsmooth regions. The construction of the nonstandard method is based on the special treatment of the interface using suitable jump conditio...
متن کاملPhone Recognition with the Mean-Covariance Restricted Boltzmann Machine
Straightforward application of Deep Belief Nets (DBNs) to acoustic modeling produces a rich distributed representation of speech data that is useful for recognition and yields impressive results on the speaker-independent TIMIT phone recognition task. However, the first-layer Gaussian-Bernoulli Restricted Boltzmann Machine (GRBM) has an important limitation, shared with mixtures of diagonalcova...
متن کاملIntegration of edge-diffraction calculations and geometrical-acoustics modeling
In time-domain simulations of sound propagation and/or scattering, it is possible to model the geometricalacoustics (GA) components and the edge-diffraction components separately and combine the results into a “total” impulse response. However, such separate calculations can limit the efficiency and accuracy of the simulations because the two components are not independent. This paper presents ...
متن کاملA graph-based Gaussian component clustering approach to unsupervised acoustic modeling
This paper describes a new approach to unsupervised acoustic modeling, that is to build acoustic models for phoneme-like sub-word units from untranscribed speech data. The proposed approach is based on Gaussian component clustering. Initially a large set of Gaussian components are estimated from the untranscribed data. Then clustering is performed to group these Gaussian components into differe...
متن کامل