@inproceedings{11724, abstract = {{In this paper we present a novel vehicle tracking method which is based on multi-stage Kalman filtering of GPS and IMU sensor data. After individual Kalman filtering of GPS and IMU measurements the estimates of the orientation of the vehicle are combined in an optimal manner to improve the robustness towards drift errors. The tracking algorithm incorporates the estimation of time-variant covariance parameters by using an iterative block Expectation-Maximization algorithm to account for time-variant driving conditions and measurement quality. The proposed system is compared to an interacting multiple model approach (IMM) and achieves improved localization accuracy at lower computational complexity. Furthermore we show how the joint parameter estimation and localizaiton can be conducted with streaming input data to be able to track vehicles in a real driving environment.}}, author = {{Bevermeier, Maik and Peschke, Sven and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE 69th Vehicular Technology Conference (VTC 2009 Spring)}}, keywords = {{computational complexity, expectation-maximisation algorithm, Global Positioning System, inertial measurement unit, inertial navigation, interacting multiple model, iterative block expectation-maximization algorithm, Kalman filters, multi-stage Kalman filter, parameter estimation, road vehicles, vehicle positioning, vehicle tracking}}, pages = {{1--5}}, title = {{{Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning}}}, doi = {{10.1109/VETECS.2009.5073634}}, year = {{2009}}, } @article{11938, abstract = {{In this paper, parameter estimation of a state-space model of noise or noisy speech cepstra is investigated. A blockwise EM algorithm is derived for the estimation of the state and observation noise covariance from noise-only input data. It is supposed to be used during the offline training mode of a speech recognizer. Further a sequential online EM algorithm is developed to adapt the observation noise covariance on noisy speech cepstra at its input. The estimated parameters are then used in model-based speech feature enhancement for noise-robust automatic speech recognition. Experiments on the AURORA4 database lead to improved recognition results with a linear state model compared to the assumption of stationary noise.}}, author = {{Windmann, Stefan and Haeb-Umbach, Reinhold}}, journal = {{IEEE Transactions on Audio, Speech, and Language Processing}}, keywords = {{AURORA4 database, blockwise EM algorithm, covariance analysis, linear state model, noise covariance, noise-robust automatic speech recognition, noisy speech cepstra, offline training mode, parameter estimation, speech recognition, speech recognition equipment, speech recognizer, state-space methods, state-space model}}, number = {{8}}, pages = {{1577--1590}}, title = {{{Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition}}}, doi = {{10.1109/TASL.2009.2023172}}, volume = {{17}}, year = {{2009}}, } @inproceedings{11935, abstract = {{The generalized sidelobe canceller by Griffith and Jim is a robust beamforming method to enhance a desired (speech) signal in the presence of stationary noise. Its performance depends to a high degree on the construction of the blocking matrix which produces noise reference signals for the subsequent adaptive interference canceller. Especially in reverberated environments the beamformer may suffer from signal leakage and reduced noise suppression. In this paper a new blocking matrix is proposed. It is based on a generalized eigenvalue problem whose solution provides an indirect estimation of the transfer functions from the source to the sensors. The quality of the new generalized eigenvector blocking matrix is studied in simulated rooms with different reverberation times and is compared to alternatives proposed in the literature.}}, author = {{Warsitz, Ernst and Krueger, Alexander and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)}}, keywords = {{adaptive interference canceller, adaptive signal processing, array signal processing, beamforming method, eigenvalues and eigenfunctions, generalized eigenvector blocking matrix, generalized sidelobe canceller, interference suppression, matrix algebra, noise suppression, speech enhancement, transfer function estimation, transfer functions}}, pages = {{73--76}}, title = {{{Speech enhancement with a new generalized eigenvector blocking matrix for application in a generalized sidelobe canceller}}}, doi = {{10.1109/ICASSP.2008.4517549}}, year = {{2008}}, } @inproceedings{11785, abstract = {{In this paper we present a novel channel impulse response estimation technique for block-oriented OFDM transmission based on combining estimators: the estimates provided by a Kalman filter operating in the time domain and a Wiener filter in the frequency domain are optimally combined by taking into account their estimated error covariances. The resulting estimator turns out to be identical to the MAP estimator of correlated jointly Gaussian mean vectors. Different variants of the proposed scheme are experimentally investigated in an EEEE 802.11a-like system setup. They compare favourably with known approaches from the literature resulting in reduced mean square estimation error and bit error rate. Further, robustness and complexity issues are discussed}}, author = {{Haeb-Umbach, Reinhold and Bevermeier, Maik}}, booktitle = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2007)}}, keywords = {{bit error rate, block-oriented OFDM transmission, channel estimation, channel impulse response estimation, combining estimators, error statistics, frequency domain estimation, Gaussian mean vectors, Gaussian processes, Kalman filter, Kalman filters, MAP estimator, maximum likelihood estimation, OFDM channel estimation, OFDM modulation, time domain estimation, time-frequency analysis, Wiener filter, Wiener filters}}, pages = {{III--277--III--280}}, title = {{{OFDM Channel Estimation Based on Combined Estimation in Time and Frequency Domain}}}, doi = {{10.1109/ICASSP.2007.366526}}, volume = {{3}}, year = {{2007}}, } @inproceedings{11883, abstract = {{In this paper, we experimentally evaluate algorithms for velocity estimation of a GSM 900 mobile terminal which are based on the analysis of the statistical properties of the fast fading process. It is shown how theses statistics can be obtained from the training sequences present in downlink transmission bursts without establishing an active connection. Realistic simulations of a GSM channel according to the COST 207 channel models have been conducted. These models incorporate effects like multipath propagation, fading, cochannel interference and additive noise. It is shown that velocity estimation by searching for the maximum slope of the power density spectrum of the fast fading performs best.}}, author = {{Peschke, Sven and Haeb-Umbach, Reinhold}}, booktitle = {{4th Workshop on Positioning Navigation and Communication (WPNC 2007)}}, keywords = {{additive noise, cellular radio, channel estimation, cochannel interference, COST 207 channel models, downlink transmission bursts, fading channels, fading process, GSM downlink signalling, mobile terminals, multipath channels, multipath propagation, power density spectrum, statistical analysis, statistical properties, telecommunication links, telecommunication terminals, velocity estimation}}, pages = {{217--222}}, title = {{{Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling}}}, doi = {{10.1109/WPNC.2007.353637}}, year = {{2007}}, } @article{11927, abstract = {{Maximizing the output signal-to-noise ratio (SNR) of a sensor array in the presence of spatially colored noise leads to a generalized eigenvalue problem. While this approach has extensively been employed in narrowband (antenna) array beamforming, it is typically not used for broadband (microphone) array beamforming due to the uncontrolled amount of speech distortion introduced by a narrowband SNR criterion. In this paper, we show how the distortion of the desired signal can be controlled by a single-channel post-filter, resulting in a performance comparable to the generalized minimum variance distortionless response beamformer, where arbitrary transfer functions relate the source and the microphones. Results are given both for directional and diffuse noise. A novel gradient ascent adaptation algorithm is presented, and its good convergence properties are experimentally revealed by comparison with alternatives from the literature. A key feature of the proposed beamformer is that it operates blindly, i.e., it neither requires knowledge about the array geometry nor an explicit estimation of the transfer functions from source to sensors or the direction-of-arrival.}}, author = {{Warsitz, Ernst and Haeb-Umbach, Reinhold}}, journal = {{IEEE Transactions on Audio, Speech, and Language Processing}}, keywords = {{acoustic signal processing, arbitrary transfer function, array signal processing, blind acoustic beamforming, direction-of-arrival, direction-of-arrival estimation, eigenvalues and eigenfunctions, generalized eigenvalue decomposition, gradient ascent adaptation algorithm, microphone arrays, microphones, narrowband array beamforming, sensor array, single-channel post-filter, spatially colored noise, transfer functions}}, number = {{5}}, pages = {{1529--1539}}, title = {{{Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition}}}, doi = {{10.1109/TASL.2007.898454}}, volume = {{15}}, year = {{2007}}, } @inproceedings{11824, abstract = {{Soft-feature based speech recognition, which is an example of uncertainty decoding, has been proven to be a robust error mitigation method for distributed speech recognition over wireless channels exhibiting bit errors. In this paper we extend this concept to packet-oriented transmissions. The a posteriori probability density function of the lost feature vector, given the closest received neighbours, is computed. In the experiments, the nearest frame repetition, which is shown to be equivalent to the MAP estimate, outperforms the MMSE estimate for long bursts. Taking the variance into account at the speech recognition stage results in superior performance compared to classical schemes using point estimates. A computationally and memory efficient implementation of the proposed packet loss compensation scheme based on table lookup is presented}}, author = {{Ion, Valentin and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)}}, keywords = {{distributed speech recognition, least mean squares methods, MAP estimate, maximum likelihood estimation, MMSE estimate, packet loss compensation scheme, packet switched communication, posteriori probability density function, robust error mitigation method, soft-features, speech recognition, table lookup, voice communication, wireless channels}}, pages = {{I}}, title = {{{An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features}}}, doi = {{10.1109/ICASSP.2006.1659984}}, volume = {{1}}, year = {{2006}}, } @inproceedings{11930, abstract = {{For human-machine interfaces in distant-talking environments multichannel signal processing is often employed to obtain an enhanced signal for subsequent processing. In this paper we propose a novel adaptation algorithm for a filter-and-sum beamformer to adjust the coefficients of FIR filters to changing acoustic room impulses, e.g. due to speaker movement. A deterministic and a stochastic gradient ascent algorithm are derived from a constrained optimization problem, which iteratively estimates the eigenvector corresponding to the largest eigenvalue of the cross power spectral density of the microphone signals. The method does not require an explicit estimation of the speaker location. The experimental results show fast adaptation and excellent robustness of the proposed algorithm.}}, author = {{Warsitz, Ernst and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005)}}, keywords = {{acoustic filter-and-sum beamforming, acoustic room impulses, acoustic signal processing, adaptive principal component analysis, adaptive signal processing, architectural acoustics, constrained optimization problem, cross power spectral density, deterministic algorithm, deterministic algorithms, distant-talking environments, eigenvalues and eigenfunctions, eigenvector, enhanced signal, filter-and-sum beamformer, FIR filter coefficients, FIR filter coefficients, FIR filters, gradient methods, human-machine interfaces, iterative estimation, iterative methods, largest eigenvalue, microphone signals, multichannel signal processing, optimisation, principal component analysis, spectral analysis, stochastic gradient ascent algorithm, stochastic processes}}, pages = {{iv/797--iv/800 Vol. 4}}, title = {{{Acoustic filter-and-sum beamforming by adaptive principal component analysis}}}, doi = {{10.1109/ICASSP.2005.1416129}}, volume = {{4}}, year = {{2005}}, } @inproceedings{11931, abstract = {{The paper is concerned with binaural signal processing for a bimodal human-robot interface with hearing and vision. The two microphone signals are processed to obtain an enhanced single-channel input signal for the subsequent speech recognizer and to localize the acoustic source, an important information for establishing a natural human-robot communication. We utilize a robust adaptive algorithm for filter-and-sum beamforming (FSB) and extract speaker direction information from the resulting FIR filter coefficients. Further, particle filtering is applied which conducts a nonlinear Bayesian tracking of speaker movement. Good location accuracy can be achieved even in highly reverberant environments. The results obtained outperform the conventional generalized cross correlation (GCC) method.}}, author = {{Warsitz, Ernst and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE Workshop on Multimedia Signal Processing (MMSP 2004)}}, keywords = {{bimodal human-robot interface, binaural signal processing, enhanced single-channel input signal, filter-and-sum beamforming, filtering theory, FIR filter coefficient, generalized cross correlation method, microphones, microphone signal, nonlinear Bayesian tracking, particle filtering, robust adaptive algorithm, robust speaker direction estimation, signal processing, speech enhancement, speech recognition, speech recognizer, user interfaces}}, pages = {{367--370}}, title = {{{Robust speaker direction estimation with particle filtering}}}, doi = {{10.1109/MMSP.2004.1436569}}, year = {{2004}}, } @article{11778, abstract = {{In this paper, it is shown that a correlation criterion is the appropriate criterion for bottom-up clustering to obtain broad phonetic class regression trees for maximum likelihood linear regression (MLLR)-based speaker adaptation. The correlation structure among speech units is estimated on the speaker-independent training data. In adaptation experiments the tree outperformed a regression tree obtained from clustering according to closeness in acoustic space and achieved results comparable with those of a manually designed broad phonetic class tree}}, author = {{Haeb-Umbach, Reinhold}}, journal = {{IEEE Transactions on Speech and Audio Processing}}, keywords = {{acoustic space, adaptation experiments, automatic generation, bottom-up clustering, broad phonetic class regression trees, correlation criterion, correlation methods, maximum likelihood estimation, maximum likelihood linear regression based speaker adaptation, MLLR adaptation, pattern clustering, phonetic regression class trees, speaker-independent training data, speech recognition, speech units, statistical analysis, trees (mathematics)}}, number = {{3}}, pages = {{299--302}}, title = {{{Automatic generation of phonetic regression class trees for MLLR adaptation}}}, doi = {{10.1109/89.906003}}, volume = {{9}}, year = {{2001}}, }