@inproceedings{11915, abstract = {{This Paper deals with a new Technique for multi-channel separation of speech signals from convolutive mixtures under coherent noise. We demonstrate how the scaled transfer functions from the sources to the microphones can be estimated even in the presence of stationary coherent noise. The key to this are generalized eigenvalue decompositions of the power spectral density (PSD) matrices of the noisy speech and noise-only microphone signals with a controlled estimation of these matrices exploiting time-frequency sparseness of the speech sources. Separation is further improved by subsequent Gram-Schmidt orthogonalization which places spatial nulls at the interferers{\rq} directions, while noise reduction is improved by employing a novel blocking matrix and adaptive interference canceller in a Generalized Sidelobe Canceller (GSC)-like structure. We report promising experimental results for 2 speech sources with significant coherent noise in reverberant environments (RT60=0oms..500ms).}}, author = {{Tran Vu, Dang Hai and Krueger, Alexander and Haeb-Umbach, Reinhold}}, booktitle = {{International Workshop on Acoustic Echo and Noise Control (IWAENC 2008)}}, title = {{{Generalized Eigenvector Blind Speech Separation Under Coherent Noise In A GSC Configuration}}}, year = {{2008}}, } @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{11939, abstract = {{In this paper a switching linear dynamical model (SLDM) approach for speech feature enhancement is improved by employing more accurate models for the dynamics of speech and noise. The model of the clean speech feature trajectory is improved by augmenting the state vector to capture information derived from the delta features. Further a hidden noise state variable is introduced to obtain a more elaborated model for the noise dynamics. Approximate Bayesian inference in the SLDM is carried out by a bank of extended Kalman filters, whose outputs are combined according to the a posteriori probability of the individual state models. Experimental results on the AURORA2 database show improved recognition accuracy.}}, author = {{Windmann, Stefan and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)}}, keywords = {{a posteriori probability, AURORA2 database, Bayesian inference, Bayes methods, channel bank filters, extended Kalman filter banks, hidden noise state variable, Kalman filters, noise dynamics, speech enhancement, speech feature enhancement, speech feature trajectory, switching linear dynamical model approach}}, pages = {{4409--4412}}, title = {{{Modeling the dynamics of speech and noise for speech feature enhancement in ASR}}}, doi = {{10.1109/ICASSP.2008.4518633}}, year = {{2008}}, } @article{11940, abstract = {{In this paper, the noise estimation for model-based speech feature enhancement in automatic speech recognition (ASR) is investigated. Beside a stationary noise prior, three linear state space models for the (cepstral) noise process are considered. We have derived novel EM algorithms for the estimation of the noise model parameters: A blockwise EM algorithm is applied on noise-only input data. It is supposed to be used during the offline training mode of the recognizer. Further a sequential online EM algorithm is employed to adapt the observation variance in recognition mode which works as well under the asumption of a stationary noise prior and a linear state model for the noise. Experiments on the AURORA4 database lead to improved recognition results with the new state model compared to the assumption of stationary noise.}}, author = {{Windmann, Stefan and Haeb-Umbach, Reinhold}}, journal = {{2008 ITG Conference on Voice Communication (SprachKommunikation)}}, pages = {{1--4}}, title = {{{A novel approach to noise estimation in model-based speech feature enhancement}}}, year = {{2008}}, } @article{11944, abstract = {{In this paper, a novel segmental Hidden Markov Model (HMM) is proposed. The model is based on a modified emission density where additional statistical dependencies between subsequent frames of the speech signal are considered. In the following we derive an effective search strategy for the modified statistical model. Further an approach to parameter reduction is introduced. Experiments were carried out on the AURORA2 database where consistent im}}, author = {{Windmann, Stefan and Haeb-Umbach, Reinhold and Leutnant, Volker}}, journal = {{2008 ITG Conference on Voice Communication (SprachKommunikation)}}, pages = {{1--4}}, title = {{{A segmental HMM based on a modified emission probability}}}, year = {{2008}}, } @inproceedings{11720, author = {{Bevermeier, Maik and Ebel, Tobias and Haeb-Umbach, Reinhold}}, booktitle = {{Multi-Carrier Spread Spectrum 2007}}, title = {{{Channel Estimation by Exploiting Sublayer Information in OFDM Systems}}}, year = {{2007}}, } @inproceedings{11722, author = {{Bevermeier, Maik and Haeb-Umbach, Reinhold}}, booktitle = {{Multi-Carrier Spread Spectrum 2007}}, title = {{{Combined Time and Frequency Domain OFDM Channel Estimation}}}, year = {{2007}}, } @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}}, } @article{11799, abstract = {{In this paper, we propose a novel similarity measure to be used for localizing mobile terminals by comparing measured signal power levels with a database of predictions. The proposed measure provides the possibility to incorporate inherent information about signal power level measurements requested by the serving base station but not reported by the mobile terminal. Increased positioning accuracy was observed both in simulations and with real field data}}, author = {{Haeb-Umbach, Reinhold and Peschke, Sven}}, journal = {{IEEE Transactions on Vehicular Technology}}, keywords = {{cellular phone positioning, cellular radio, measured signal power levels, mobile handsets, mobility management (mobile radio)}}, number = {{1}}, pages = {{368--372}}, title = {{{A Novel Similarity Measure for Positioning Cellular Phones by a Comparison With a Database of Signal Power Levels}}}, doi = {{10.1109/TVT.2006.889563}}, volume = {{56}}, year = {{2007}}, } @inproceedings{11822, author = {{Ion, Valentin and Haeb-Umbach, Reinhold}}, booktitle = {{Interspeech 2007}}, title = {{{Multi-Resolution Soft Features for Channel-Robust Distributed Speech Recognition}}}, 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{11934, author = {{Warsitz, Ernst and Haeb-Umbach, Reinhold and Tran Vu, Dang Hai}}, booktitle = {{Interspeech 2007}}, title = {{{Blind Adaptive Principal Eigenvector Beamforming for Acoustical Source Separation}}}, year = {{2007}}, } @inproceedings{11941, author = {{Windmann, Stefan and Haeb-Umbach, Reinhold}}, booktitle = {{Interspeech 2007}}, title = {{{An Approach to Iterative Speech Feature Enhancement and Recognition}}}, year = {{2007}}, } @inproceedings{11893, author = {{Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{Interspeech 2007}}, title = {{{Joint Speaker Segmentation, Localization and Identification for Streaming Audio}}}, year = {{2007}}, } @inproceedings{11901, author = {{Schmalenstroeer, Joerg and Leutnant, Volker and Haeb-Umbach, Reinhold}}, booktitle = {{AMI-07 - European Conference on Ambient Intelligence}}, title = {{{Amigo Context Management Service with Applications in Ambient Communication Scenarios}}}, year = {{2007}}, } @inproceedings{11933, author = {{Warsitz, Ernst and Haeb-Umbach, Reinhold and Schmalenstroeer, Joerg}}, booktitle = {{33. Deutsche Jahrestagung fuer Akustik (DAGA 2007)}}, title = {{{Zweistufige Sprache/Pause-Detektion in stark gestoerter Umgebung}}}, year = {{2007}}, } @inproceedings{11902, author = {{Schmalenstroeer, Joerg and Warsitz, Ernst and Haeb-Umbach, Reinhold}}, booktitle = {{33. Deutsche Jahrestagung fuer Akustik (DAGA 2007)}}, title = {{{Projekt Amigo - Sprachsignalverarbeitung im vernetzten Haus}}}, year = {{2007}}, } @inproceedings{11823, abstract = {{In this study we evaluate transmission error compensation techniques for distributed speech recognition systems based on modification of the speech decoder. The candidates are marginalization, weighted Viterbi and our recently proposed soft-feature uncertainty decoding. For the latter, it is shown how the Bayesian speech recognition approach must be reformulated for recognition at the server side. The resulting predictive classifier is able to take account of the transmission errors by changing the contribution of the affected speech features to the acoustic score. The comparison of the experimental results has proven the superiority of our approach.}}, author = {{Ion, Valentin and Haeb-Umbach, Reinhold}}, booktitle = {{7. ITG-Fachtagung Sprachkommunikation}}, title = {{{Comparison of Decoder-based Transmission Error Compensation Techniques for Distributed Speech Recognition}}}, year = {{2006}}, } @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}}, }