No / Dynamic speech properties, such as time warping, silence removal and background noise reduction are the most challenging issues in continuous speech signal matching. Among all of them, the time warped speech signal matching is of great interest and has been a tough challenge for the researchers. The literature contains a variety of techniques to measure the similarity between speech utterances, however there are some limitations associated with these techniques. This paper introduces an adaptive framing based continuous speech tracking and similarity measurement approach that uses a Kalman filter (KF) as a robust tracker. The use of KF is novel for time warped speech signal matching and dynamic time warping. A dynamic state model is presented based on equations of linear motion. In this model, fixed length frame of input (test) speech signal is considered as a unidirectional moving object by sliding it along the template speech signal. The best matched position estimate in template speech (sample number) for corresponding test frame at current time is calculated. Simultaneously, another position observation is produced by a feature based distance metric. The position estimated by the state model is fused with the observation using KF along with the noise variances. The best estimated frame position in the template speech for the current state is calculated. Finally, forecasting of the noise variances and template frame size for next state are made according to the KF output. The experimental results demonstrate the robustness of the proposed technique in terms of time warped speech signal matching as well as in computation cost.

In noisy and complex environments, human listeners must segregate the mixture of sound sources arriving at their ears and selectively attend a single source, thereby solving a computationally difficult problem called the cocktail party problem. However, the neural mechanisms underlying these computations are still largely a mystery. Oscillatory synchronization of neuronal activity between cortical areas is thought to provide a crucial role in facilitating information transmission between spatially separated populations of neurons, enabling the formation of functional networks. In this thesis, we seek to analyze and model the functional neuronal networks underlying attention to speech stimuli and find that the Frontal Eye Fields play a central 'hub' role in the auditory spatial attention network in a cocktail party experiment. We use magnetoencephalography (MEG) to measure neural signals with high temporal precision, while sampling from the whole cortex. However, several methodological issues arise when undertaking functional connectivity analysis with MEG data. Specifically, volume conduction of electrical and magnetic fields in the brain complicates interpretation of results. We compare several approaches through simulations, and analyze the trade-offs among various measures of neural phase-locking in the presence of volume conduction. We use these insights to study functional networks in a cocktail party experiment. We then construct a linear dynamical system model of neural responses to ongoing speech. Using this model, we are able to correctly predict which of two speakers is being attended by a listener. We then apply this model to data from a task where people were attending to stories with synchronous and scrambled videos of the speakers' faces to explore how the presence of visual information modifies the underlying neuronal mechanisms of speech perception. This model allows us to probe neural processes as subjects listen to long stimuli, without the need for a trial-based experimental design. We model the neural activity with latent states, and model the neural noise spectrum and functional connectivity with multivariate autoregressive dynamics, along with impulse responses for external stimulus processing. We also develop a new regularized Expectation-Maximization (EM) algorithm to fit this model to electroencephalography (EEG) data.

Dynamic speech properties such as time warping, silence removal and background noise interference are the most challenging issues in continuous speech signal matching. Among all of them, the time warped speech signal matching is of great interest and has been a tough challenge for the researchers. An adaptive framing based continuous speech tracking and similarity measurement approach is introduced in this work following a comprehensive research conducted in the diverse areas of speech processing. A dynamic state model is introduced based on system of linear motion equations which models the input (test) speech signal frame as a unidirectional moving object along the template speech signal. The most similar corresponding frame position in the template speech is estimated which is fused with a feature based similarity observation and the noise variances using a Kalman filter. The Kalman filter provides the final estimated frame position in the template speech at current time which is further used for prediction of a new frame size for the next step. In addition, a keyword spotting approach is proposed by introducing wavelet decomposition based dynamic noise filter and combination of beliefs. The Dempster’s theory of belief combination is deployed for the first time in relation to keyword spotting task. Performances for both; speech tracking and keyword spotting approaches are evaluated using the statistical metrics and gold standards for the binary classification. Experimental results proved the superiority of the proposed approaches over the existing methods.

Dynamic speech properties such as time warping, silence removal and background noise interference are the most challenging issues in continuous speech signal matching. Among all of them, the time warped speech signal matching is of great interest and has been a tough challenge for the researchers. An adaptive framing based continuous speech tracking and similarity measurement approach is introduced in this work following a comprehensive research conducted in the diverse areas of speech processing. A dynamic state model is introduced based on system of linear motion equations which models the input (test) speech signal frame as a unidirectional moving object along the template speech signal. The most similar corresponding frame position in the template speech is estimated which is fused with a feature based similarity observation and the noise variances using a Kalman filter. The Kalman filter provides the final estimated frame position in the template speech at current time which is further used for prediction of a new frame size for the next step. In addition, a keyword spotting approach is proposed by introducing wavelet decomposition based dynamic noise filter and combination of beliefs. The Dempster’s theory of belief combination is deployed for the first time in relation to keyword spotting task. Performances for both; speech tracking and keyword spotting approaches are evaluated using the statistical metrics and gold standards for the binary classification. Experimental results proved the superiority of the proposed approaches over the existing methods. / The appendices files are not available online.