@article{11861,
  abstract     = {{In this contribution we present a theoretical and experimental investigation into the effects of reverberation and noise on features in the logarithmic mel power spectral domain, an intermediate stage in the computation of the mel frequency cepstral coefficients, prevalent in automatic speech recognition (ASR). Gaining insight into the complex interaction between clean speech, noise, and noisy reverberant speech features is essential for any ASR system to be robust against noise and reverberation present in distant microphone input signals. The findings are gathered in a probabilistic formulation of an observation model which may be used in model-based feature compensation schemes. The proposed observation model extends previous models in three major directions: First, the contribution of additive background noise to the observation error is explicitly taken into account. Second, an energy compensation constant is introduced which ensures an unbiased estimate of the reverberant speech features, and, third, a recursive variant of the observation model is developed resulting in reduced computational complexity when used in model-based feature compensation. The experimental section is used to evaluate the accuracy of the model and to describe how its parameters can be determined from test data.}},
  author       = {{Leutnant, Volker and Krueger, Alexander and Haeb-Umbach, Reinhold}},
  issn         = {{2329-9290}},
  journal      = {{IEEE/ACM Transactions on Audio, Speech, and Language Processing}},
  keywords     = {{computational complexity, reverberation, speech recognition, automatic speech recognition, background noise, clean speech, computational complexity, energy compensation, logarithmic mel power spectral domain, mel frequency cepstral coefficients, microphone input signals, model-based feature compensation schemes, noisy reverberant speech automatic recognition, noisy reverberant speech features, reverberation, Atmospheric modeling, Computational modeling, Noise, Noise measurement, Reverberation, Speech, Vectors, Model-based feature compensation, observation model for reverberant and noisy speech, recursive observation model, robust automatic speech recognition}},
  number       = {{1}},
  pages        = {{95--109}},
  title        = {{{A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech}}},
  doi          = {{10.1109/TASLP.2013.2285480}},
  volume       = {{22}},
  year         = {{2014}},
}

@article{11862,
  abstract     = {{In this contribution we extend a previously proposed Bayesian approach for the enhancement of reverberant logarithmic mel power spectral coefficients for robust automatic speech recognition to the additional compensation of background noise. A recently proposed observation model is employed whose time-variant observation error statistics are obtained as a side product of the inference of the a posteriori probability density function of the clean speech feature vectors. Further a reduction of the computational effort and the memory requirements are achieved by using a recursive formulation of the observation model. The performance of the proposed algorithms is first experimentally studied on a connected digits recognition task with artificially created noisy reverberant data. It is shown that the use of the time-variant observation error model leads to a significant error rate reduction at low signal-to-noise ratios compared to a time-invariant model. Further experiments were conducted on a 5000 word task recorded in a reverberant and noisy environment. A significant word error rate reduction was obtained demonstrating the effectiveness of the approach on real-world data.}},
  author       = {{Leutnant, Volker and Krueger, Alexander and Haeb-Umbach, Reinhold}},
  journal      = {{IEEE Transactions on Audio, Speech, and Language Processing}},
  keywords     = {{Bayes methods, compensation, error statistics, reverberation, speech recognition, Bayesian feature enhancement, background noise, clean speech feature vectors, compensation, connected digits recognition task, error statistics, memory requirements, noisy reverberant data, posteriori probability density function, recursive formulation, reverberant logarithmic mel power spectral coefficients, robust automatic speech recognition, signal-to-noise ratios, time-variant observation, word error rate reduction, Robust automatic speech recognition, model-based Bayesian feature enhancement, observation model for reverberant and noisy speech, recursive observation model}},
  number       = {{8}},
  pages        = {{1640--1652}},
  title        = {{{Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition}}},
  doi          = {{10.1109/TASL.2013.2258013}},
  volume       = {{21}},
  year         = {{2013}},
}

@inproceedings{11864,
  abstract     = {{In this work, an observation model for the joint compensation of noise and reverberation in the logarithmic mel power spectral density domain is considered. It relates the features of the noisy reverberant speech to those of the non-reverberant speech and the noise. In contrast to enhancement of features only corrupted by reverberation (reverberant features), enhancement of noisy reverberant features requires a more sophisticated model for the error introduced by the proposed observation model. In a first consideration, it will be shown that this error is highly dependent on the instantaneous ratio of the power of reverberant speech to the power of the noise and, moreover, sensitive to the phase between reverberant speech and noise in the short-time discrete Fourier domain. Afterwards, a statistically motivated approach will be presented allowing for the model of the observation error to be inferred from the error model previously used for the reverberation only case. Finally, the developed observation error model will be utilized in a Bayesian feature enhancement scheme, leading to improvements in word accuracy on the AURORA5 database.}},
  author       = {{Leutnant, Volker and Krueger, Alexander and Haeb-Umbach, Reinhold}},
  booktitle    = {{Signal Processing, Communications and Computing (ICSPCC), 2012 IEEE International Conference on}},
  keywords     = {{Robust Automatic Speech Recognition, Bayesian feature enhancement, observation model for reverberant and noisy speech}},
  title        = {{{A Statistical Observation Model For Noisy Reverberant Speech Features and its Application to Robust ASR}}},
  year         = {{2012}},
}

@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}},
}