@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}},
}

@article{11850,
  abstract     = {{In this paper, we present a novel blocking matrix and fixed beamformer design for a generalized sidelobe canceler for speech enhancement in a reverberant enclosure. They are based on a new method for estimating the acoustical transfer function ratios in the presence of stationary noise. The estimation method relies on solving a generalized eigenvalue problem in each frequency bin. An adaptive eigenvector tracking utilizing the power iteration method is employed and shown to achieve a high convergence speed. Simulation results demonstrate that the proposed beamformer leads to better noise and interference reduction and reduced speech distortions compared to other blocking matrix designs from the literature.}},
  author       = {{Krueger, Alexander and Warsitz, Ernst and Haeb-Umbach, Reinhold}},
  journal      = {{IEEE Transactions on Audio, Speech, and Language Processing}},
  keywords     = {{acoustical transfer function ratio, adaptive eigenvector tracking, array signal processing, beamformer design, blocking matrix, eigenvalues and eigenfunctions, eigenvector-based transfer function ratios estimation, generalized sidelobe canceler, interference reduction, iterative methods, power iteration method, reduced speech distortions, reverberant enclosure, reverberation, speech enhancement, stationary noise}},
  number       = {{1}},
  pages        = {{206--219}},
  title        = {{{Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation}}},
  doi          = {{10.1109/TASL.2010.2047324}},
  volume       = {{19}},
  year         = {{2011}},
}

@article{11937,
  abstract     = {{In automatic speech recognition, hidden Markov models (HMMs) are commonly used for speech decoding, while switching linear dynamic models (SLDMs) can be employed for a preceding model-based speech feature enhancement. In this paper, these model types are combined in order to obtain a novel iterative speech feature enhancement and recognition architecture. It is shown that speech feature enhancement with SLDMs can be improved by feeding back information from the HMM to the enhancement stage. Two different feedback structures are derived. In the first, the posteriors of the HMM states are used to control the model probabilities of the SLDMs, while in the second they are employed to directly influence the estimate of the speech feature distribution. Both approaches lead to improvements in recognition accuracy both on the AURORA2 and AURORA4 databases compared to non-iterative speech feature enhancement with SLDMs. It is also shown that a combination with uncertainty decoding further enhances performance.}},
  author       = {{Windmann, Stefan and Haeb-Umbach, Reinhold}},
  journal      = {{IEEE Transactions on Audio, Speech, and Language Processing}},
  keywords     = {{AURORA2 databases, AURORA4 databases, automatic speech recognition, feedback structures, hidden Markov models, HMM, iterative methods, iterative speech feature enhancement, model probabilities, speech decoding, speech enhancement, speech feature distribution, speech recognition, switching linear dynamic models}},
  number       = {{5}},
  pages        = {{974--984}},
  title        = {{{Approaches to Iterative Speech Feature Enhancement and Recognition}}},
  doi          = {{10.1109/TASL.2009.2014894}},
  volume       = {{17}},
  year         = {{2009}},
}

@inproceedings{11943,
  abstract     = {{A marginalized particle filter is proposed for performing single channel speech enhancement with a non-linear dynamic state model. The system consists of a particle filter for tracking line spectral pair (LSP) parameters and a Kalman filter per particle for speech enhancement. The state model for the LSPs has been learnt on clean speech training data. In our approach parameters and speech samples are processed at different time scales by assuming the parameters to be constant for small blocks of data. Further enhancement is obtained by an iteration which can be applied on these small blocks. The experiments show that similar SNR gains are obtained as with the Kalman-LM-iterative algorithm. However better values of the noise level and the log-spectral distance are achieved}},
  author       = {{Windmann, Stefan and Haeb-Umbach, Reinhold}},
  booktitle    = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)}},
  keywords     = {{clean speech training data, iterative methods, iterative speech enhancement, Kalman filter, Kalman filters, Kalman-LM-iterative algorithm, line spectral pair parameters, log-spectral distance, marginalized particle filter, noise level, nonlinear dynamic state speech model, particle filtering (numerical methods), single channel speech enhancement, SNR gains, speech enhancement, speech samples}},
  pages        = {{I}},
  title        = {{{Iterative Speech Enhancement using a Non-Linear Dynamic State Model of Speech and its Parameters}}},
  doi          = {{10.1109/ICASSP.2006.1660058}},
  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}},
}