Neural Computation of Direction-Of-Arrival of Sound
نویسندگان
چکیده
One of issues related to videoconferencing is addressed in the paper, namely the problem of sound source localization. A new neural approach for estimation direction of arrival (DOA) is presented and discussed therein. The introduced algorithms are based on various types and structures of neural networks, including feedforward and recurrent ones. Considerations of the proposed DOA estimation are supported by some of the results of numerous experiments, carried out using audio material recorded in an anechoic chamber and acoustically adopted room. The results are briefly discussed. Key-Words: sound source localization, feedforward & recurrent neural networks
منابع مشابه
A New Algorithm for the Deinterleaving of Radar Pulses
This paper presents a new algorithm for the deinterleaving of radar signals, based on the direction of arrival (DOA), carrier frequency (RF), and time of arrival (TOA). The algorithm is applied to classic (constant), jitter, staggered, and dwell switch pulse repetition interval (PRI) signals. This algorithm consists of two stages. In the first stage, a Kohonen neural network clusters the receiv...
متن کاملتعیین حد پائین واریانس خطای تخمین برای زاویه سیگنال دریافتی با استفاده از روش CRB در آنتن های آرایه ای
One of the important issues in many of array systems such as Radar, Sonar, Mobile, and satellite telecommunications is the estimation of DOA of narrowband received signal. CRB is very important in evaluation of parameter estimation. CRB is the lower bound estimation error variance for any unbiased estimation. In this paper, the array antenna with equal distance arrays is extended in two separat...
متن کاملAcoustic Source Localization Based on Time-delay Estimation Method
Paper deals with acoustic source localization using microphone array using time-delay estimation method. It describes main requirements, hardware design of the microphone units with automatic gain control preamplifiers with integrated anti-aliasing filters and finally its connection to standard personal computer equipped with Advantech PCI1716 multifunction data acquisition card. Next part of t...
متن کاملA Neural Network Filter to Estimate the Doa of Small Targets
Direction-of-arrival (DOA) estimation is an important problem in many applications such as communication and navigation. Many methods have been presented for this problem. The Maximum Likelihood (ML) is one of the good solutions. But, in traditional algorithms for ML Nonetheless, the computational load is very heavy and multivariate nonlinear maximization problem is serious. To deal with these ...
متن کاملEffect of sound classification by neural networks in the recognition of human hearing
In this paper, we focus on two basic issues: (a) the classification of sound by neural networks based on frequency and sound intensity parameters (b) evaluating the health of different human ears as compared to of those a healthy person. Sound classification by a specific feed forward neural network with two inputs as frequency and sound intensity and two hidden layers is proposed. This process...
متن کامل