Abstract. Real world applications such as hands-free dialling in cars may have to deal with potentially very noisy environments. Existing state-of-the-art solutions to this problem use featurebased HMMs, with a preprocessing stage to clean the noisy signal. However, the effect that raw signal noise has on the induced HMM features is poorly understood, and limits the performance of the HMM system. An alternative to feature-based HMMs is to model the raw signal, which has the potential advantage that including an explicit noise model is straightforward. Here we jointly model the dynamics of both the raw speech signal and the noise, using a Switching Linear Dynamical System (SLDS). The new model was tested on isolated digit utterances corrupted by Gaussian noise. Contrary to the Autoregressive HMM and its derivatives, which provides a model of uncorrupted raw speech, the SLDS is comparatively noise robust and also significantly outperforms a state-of-the-art feature-based HMM. The computational complexity of the SLDS scales exponentially with the length of the time series. To counter this we use Expectation Correction which provides a stable and accurate linear-time approximation for this important class of models, aiding their further application in acoustic modelling.
This paper proposes a simple, computationally efficient 2-mixture model approach to discriminate between speech and background noise at the magnitude spectrogram level. It is directly derived from observations on real data, and can be used in a fully unsupervised manner, with the EM algorithm. In this paper, the 2-mixture model is used in an "Unsupervised Spectral Subtraction" scheme that can be applied as a pre-processing step for any acoustic feature extraction scheme, such as MFCCs or PLP. The goal is to improve noise-robustness of the acoustic features. Experimental results on both OGI Numbers 95 and Aurora 2 tasks yielded a major improvement on all noise conditions, while retaining a similar performance on clean conditions.
It has been shown that uniform as well as non-uniform cellular automata (CA) can be evolved to perform certain computational tasks. Random Boolean networks are a generalization of two-state cellular automata, where the interconnection topology and the cell's rules are specified at random.Here we present a novel analytical approach to find the local rules of random Boolean networks (RBNs) to solve the global density classification and the synchronization task from any initial configuration. We quantitatively and qualitatively compare our results with previously published work on cellular automata and show that randomly interconnected automata are computationally more efficient in solving these two global tasks. Our approach also provides convergence and quality estimates and allows the networks to be randomly rewired during operation, without affecting the global performance. Finally, we show that RBNs outperform small-world topologies on the density classification task and that they perform equally well on the synchronization task.Our novel approach and the results may have applications in designing robust complex networks and locally interacting distributed computing systems for solving global tasks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.