Robust Spelling and Digit Recognition in the Car: Switching Models and Their Like
نویسندگان
چکیده
Performance of speech recognition systems strongly degrades in the presence of background noise, like the driving noise in the interior of a car. We aim to improve noise robustness focusing on all major levels of speech recognition: feature extraction, feature enhancement, and speech modeling. Different auditory modeling concepts, speech enhancement techniques, training strategies, and model architectures are implemented in an incar digit and spelling recognition task, which considers noises produced by various car types and driving conditions. Matched conditions training and auditory modeling techniques like Perceptual Linear Prediction (PLP) are applied in order to improve recognition rates. We prove that joint speech and noise modeling with a global Switching Linear Dynamic Model (SLDM) capturing the dynamics of speech, and a Linear Dynamic Model (LDM) for noise, outperforms speech enhancement techniques like Histogram Equalization (HEQ).
منابع مشابه
Recognition of Noisy Speech: A Comparative Survey of Robust Model Architecture and Feature Enhancement
Performance of speech recognition systems strongly degrades in the presence of background noise, like the driving noise inside a car. In contrast to existing works, we aim to improve noise robustness focusing on all major levels of speech recognition: feature extraction, feature enhancement, speech modelling, and training. Thereby, we give an overview of promising auditory modelling concepts, s...
متن کاملSolving Path Following Problem for Car-Like Robot in the Presence of Sliding Effect via LMI Formulation
One of the main problems of car-like robot is robust path following in the presence of sliding effect. To tackle this problem, a robust mix H2/H∞ static state feedback control method is selected. This method is the well-known linear robust controller which is robust against external disturbance as well as model uncertainty. In this paper, the path following problem is formulated as linear matri...
متن کاملPresentation of quasi-linear piecewise selected models simultaneously with designing of bump-less optimal robust controller for nonlinear vibration control of composite plates
The idea of using quasi-linear piecewise models has been established on the decomposition of complicated nonlinear systems, simultaneously designing with local controllers. Since the proper performance and the final system close loop stability are vital in multi-model controllers designing, the main problem in multi-model controllers is the number of the local models and their position not payi...
متن کاملSwitching Linear Dynamic Models for Noise Robust In-Car Speech Recognition
Performance of speech recognition systems strongly degrades in the presence of background noise, like the driving noise in the interior of a car. We compare two different Kalman filtering approaches which attempt to improve noise robustness: Switching Linear Dynamic Models (SLDM) and Autoregressive Switching Linear Dynamical Systems (ARSLDS). Unlike previous works which are restricted on consid...
متن کاملReal Time Implementation of a License Plate Location Recognition System Based on Adaptive Morphology
License plate recognition (LPR) by using morphology has the advantage of resistance to brightness changes; high speed processing, and low complexity. However these approaches are sensitive to the distance of the plate from the camera and imaging angle. Various assumptions reported in other works might be unrealistic and cause major problems in practical experiences. In this paper we considered ...
متن کامل