@inproceedings{11716, abstract = {{The accuracy of automatic speech recognition systems in noisy and reverberant environments can be improved notably by exploiting the uncertainty of the estimated speech features using so-called uncertainty-of-observation techniques. In this paper, we introduce a new Bayesian decision rule that can serve as a mathematical framework from which both known and new uncertainty-of-observation techniques can be either derived or approximated. The new decision rule in its direct form leads to the new significance decoding approach for Gaussian mixture models, which results in better performance compared to standard uncertainty-of-observation techniques in different additive and convolutive noise scenarios.}}, author = {{Abdelaziz, Ahmed H. and Zeiler, Steffen and Kolossa, Dorothea and Leutnant, Volker and Haeb-Umbach, Reinhold}}, booktitle = {{Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on}}, issn = {{1520-6149}}, keywords = {{Bayes methods, Gaussian processes, convolution, decision theory, decoding, noise, reverberation, speech coding, speech recognition, Bayesian decision rule, GMM, Gaussian mixture models, additive noise scenarios, automatic speech recognition systems, convolutive noise scenarios, decoding approach, mathematical framework, reverberant environments, significance decoding, speech feature estimation, uncertainty-of-observation techniques, Hidden Markov models, Maximum likelihood decoding, Noise, Speech, Speech recognition, Uncertainty, Uncertainty-of-observation, modified imputation, noise robust speech recognition, significance decoding, uncertainty decoding}}, pages = {{6827--6831}}, title = {{{GMM-based significance decoding}}}, doi = {{10.1109/ICASSP.2013.6638984}}, year = {{2013}}, } @inproceedings{11740, abstract = {{In this contribution we derive the Maximum A-Posteriori (MAP) estimates of the parameters of a Gaussian Mixture Model (GMM) in the presence of noisy observations. We assume the distortion to be white Gaussian noise of known mean and variance. An approximate conjugate prior of the GMM parameters is derived allowing for a computationally efficient implementation in a sequential estimation framework. Simulations on artificially generated data demonstrate the superiority of the proposed method compared to the Maximum Likelihood technique and to the ordinary MAP approach, whose estimates are corrected by the known statistics of the distortion in a straightforward manner.}}, author = {{Chinaev, Aleksej and Haeb-Umbach, Reinhold}}, booktitle = {{38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, keywords = {{Gaussian noise, maximum likelihood estimation, parameter estimation, GMM parameter, Gaussian mixture model, MAP estimation, Map-based estimation, maximum a-posteriori estimation, maximum likelihood technique, noisy observation, sequential estimation framework, white Gaussian noise, Additive noise, Gaussian mixture model, Maximum likelihood estimation, Noise measurement, Gaussian mixture model, Maximum a posteriori estimation, Maximum likelihood estimation}}, pages = {{3352--3356}}, title = {{{MAP-based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations}}}, doi = {{10.1109/ICASSP.2013.6638279}}, year = {{2013}}, } @inproceedings{11742, abstract = {{In this paper we present an improved version of the recently proposed Maximum A-Posteriori (MAP) based noise power spectral density estimator. An empirical bias compensation and bandwidth adjustment reduce bias and variance of the noise variance estimates. The main advantage of the MAP-based postprocessor is its low estimation variance. The estimator is employed in the second stage of a two-stage single-channel speech enhancement system, where eight different state-of-the-art noise tracking algorithms were tested in the first stage. While the postprocessor hardly affects the results in stationary noise scenarios, it becomes the more effective the more nonstationary the noise is. The proposed postprocessor was able to improve all systems in babble noise w.r.t. the perceptual evaluation of speech quality performance.}}, author = {{Chinaev, Aleksej and Haeb-Umbach, Reinhold and Taghia, Jalal and Martin, Rainer}}, booktitle = {{38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, pages = {{7477--7481}}, title = {{{Improved Single-Channel Nonstationary Noise Tracking by an Optimized MAP-based Postprocessor}}}, doi = {{10.1109/ICASSP.2013.6639116}}, year = {{2013}}, } @inproceedings{11816, abstract = {{In this paper, we consider the Maximum Likelihood (ML) estimation of the parameters of a GAUSSIAN in the presence of censored, i.e., clipped data. We show that the resulting Expectation Maximization (EM) algorithm delivers virtually biasfree and efficient estimates, and we discuss its convergence properties. We also discuss optimal classification in the presence of censored data. Censored data are frequently encountered in wireless LAN positioning systems based on the fingerprinting method employing signal strength measurements, due to the limited sensitivity of the portable devices. Experiments both on simulated and real-world data demonstrate the effectiveness of the proposed algorithms.}}, author = {{Hoang, Manh Kha and Haeb-Umbach, Reinhold}}, booktitle = {{38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, keywords = {{Gaussian processes, Global Positioning System, convergence, expectation-maximisation algorithm, fingerprint identification, indoor radio, signal classification, wireless LAN, EM algorithm, ML estimation, WiFi indoor positioning, censored Gaussian data classification, clipped data, convergence properties, expectation maximization algorithm, fingerprinting method, maximum likelihood estimation, optimal classification, parameters estimation, portable devices sensitivity, signal strength measurements, wireless LAN positioning systems, Convergence, IEEE 802.11 Standards, Maximum likelihood estimation, Parameter estimation, Position measurement, Training, Indoor positioning, censored data, expectation maximization, signal strength, wireless LAN}}, pages = {{3721--3725}}, title = {{{Parameter estimation and classification of censored Gaussian data with application to WiFi indoor positioning}}}, doi = {{10.1109/ICASSP.2013.6638353}}, year = {{2013}}, } @inproceedings{11917, abstract = {{In this paper we present a speech presence probability (SPP) estimation algorithmwhich exploits both temporal and spectral correlations of speech. To this end, the SPP estimation is formulated as the posterior probability estimation of the states of a two-dimensional (2D) Hidden Markov Model (HMM). We derive an iterative algorithm to decode the 2D-HMM which is based on the turbo principle. The experimental results show that indeed the SPP estimates improve from iteration to iteration, and further clearly outperform another state-of-the-art SPP estimation algorithm.}}, author = {{Vu, Dang Hai Tran and Haeb-Umbach, Reinhold}}, booktitle = {{38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, keywords = {{correlation methods, estimation theory, hidden Markov models, iterative methods, probability, spectral analysis, speech processing, 2D HMM, SPP estimates, iterative algorithm, posterior probability estimation, spectral correlation, speech presence probability estimation, state-of-the-art SPP estimation algorithm, temporal correlation, turbo principle, two-dimensional hidden Markov model, Correlation, Decoding, Estimation, Iterative decoding, Noise, Speech, Vectors}}, pages = {{863--867}}, title = {{{Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation}}}, doi = {{10.1109/ICASSP.2013.6637771}}, year = {{2013}}, } @inproceedings{11832, abstract = {{In this paper we propose an approach to retrieve the absolute geometry of an acoustic sensor network, consisting of spatially distributed microphone arrays, from reverberant speech input. The calibration relies on direction of arrival measurements of the individual arrays. The proposed calibration algorithm is derived from a maximum-likelihood approach employing circular statistics. Since a sensor node consists of a microphone array with known intra-array geometry, we are able to obtain an absolute geometry estimate, including angles and distances. Simulation results demonstrate the effectiveness of the approach.}}, author = {{Jacob, Florian and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, keywords = {{Geometry calibration, microphone arrays, position self-calibration}}, pages = {{116--120}}, title = {{{DoA-Based Microphone Array Position Self-Calibration Using Circular Statistic}}}, doi = {{10.1109/ICASSP.2013.6637620}}, year = {{2013}}, }