@article{KinoshitaDelcroixGannotetal., author = {Kinoshita, Keisuke and Delcroix, Marc and Gannot, Sharon and Habets, Emanuel A. P. and Haeb-Umbach, Reinhold and Kellermann, Walter and Leutnant, Volker and Maas, Roland and Nakatani, Tomohiro and Raj, Bhiksha and Sehr, Armin and Yoshioka, Takuya}, title = {A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research}, series = {Eurasip journal on advances in signal processing}, volume = {2016}, journal = {Eurasip journal on advances in signal processing}, publisher = {Springer Nature}, doi = {10.1186/s13634-016-0306-6}, abstract = {In recent years, substantial progress has been made in the field of reverberant speech signal processing, including both single- and multichannel dereverberation techniques and automatic speech recognition (ASR) techniques that are robust to reverberation. In this paper, we describe the REVERB challenge, which is an evaluation campaign that was designed to evaluate such speech enhancement (SE) and ASR techniques to reveal the state-of-the-art techniques and obtain new insights regarding potential future research directions. Even though most existing benchmark tasks and challenges for distant speech processing focus on the noise robustness issue and sometimes only on a single- channel scenario, a particular novelty of the REVERB challenge is that it is carefully designed to test robustness against reverberation, based on both real, single- channel, and multichannel recordings. This challenge attracted 27 papers, which represent 25 systems specifically designed for SE purposes and 49 systems specifically designed for ASR purposes. This paper describes the problems dealt within the challenge, provides an overview of the submitted systems, and scrutinizes them to clarify what current processing strategies appear effective in reverberant speech processing.}, language = {en} } @article{MaasHuemmerSehretal., author = {Maas, Roland and Huemmer, Christian and Sehr, Armin and Kellermann, Walter}, title = {A Bayesian view on acoustic model-based techniques for robust speech recognition}, series = {EURASIP Journal on Advances in Signal Processing}, volume = {103}, journal = {EURASIP Journal on Advances in Signal Processing}, publisher = {Springer Nature}, doi = {10.1186/s13634-015-0287-x}, abstract = {This article provides a unifying Bayesian view on various approaches for acoustic model adaptation, missing feature, and uncertainty decoding that are well-known in the literature of robust automatic speech recognition. The representatives of these classes can often be deduced from a Bayesian network that extends the conventional hidden Markov models used in speech recognition. These extensions, in turn, can in many cases be motivated from an underlying observation model that relates clean and distorted feature vectors. By identifying and converting the observation models into a Bayesian network representation, we formulate the corresponding compensation rules. We thus summarize the various approaches as approximations or modifications of the same Bayesian decoding rule leading to a unified view on known derivations as well as to new formulations for certain approaches.}, language = {en} } @inproceedings{MaasThippurSehretal., author = {Maas, Roland and Thippur, Akshaya and Sehr, Armin and Kellermann, Walter}, title = {An uncertainty decoding approach to noise- and reverberation-robust speech recognition}, series = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 26-31 May 2013, Vancouver, BC, Canada : Proceedings}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 26-31 May 2013, Vancouver, BC, Canada : Proceedings}, publisher = {IEEE}, doi = {10.1109/ICASSP.2013.6639098}, pages = {7388 -- 7392}, abstract = {The generic REMOS (REverberation MOdeling for robust Speech recognition) concept is extended in this contribution to cope with additional noise components. REMOS originally embeds an explicit reverberation model into a hiddenMarkov model (HMM) leading to a relaxed conditional independence assumption for the observed feature vectors. During recognition, a nonlinear optimization problem is to be solved in order to adapt the HMMs' output probability density functions to the current reverberation conditions. The extension for additional noise components necessitates a modified numerical solver for the nonlinear optimization problem. We propose an approximation scheme based on continuous piecewise linear regression. Connected-digit recognition experiments demonstrate the potential of REMOS in reverberant and noisy environments. They furthermore reveal that the benefit of an explicit reverberation model, overcoming the conditional independence assumption, increases with increasing signal-to-noise-ratios.}, language = {en} } @article{ReindlZhengSchwarzetal., author = {Reindl, Klaus and Zheng, Yuanhang and Schwarz, Andreas and Meier, Stefan and Maas, Roland and Sehr, Armin and Kellermann, Walter}, title = {A stereophonic acoustic signal extraction scheme for noisy and reverberant environments}, series = {Computer Speech and Language}, volume = {27}, journal = {Computer Speech and Language}, number = {3}, publisher = {Elsevier}, doi = {10.1016/j.csl.2012.07.011}, pages = {726 -- 745}, abstract = {In this contribution, a novel two-channel acoustic front-end for robust automatic speech recognition in adverse acoustic environments with nonstationary interference and reverberation is proposed. From a MISO system perspective, a statistically optimum source signal extraction scheme based on the multichannel Wiener filter (MWF) is discussed for application in noisy and underdetermined scenarios. For free-field and diffuse noise conditions, this optimum scheme reduces to a Delay \& Sum beamformer followed by a single-channel Wiener postfilter. Scenarios with multiple simultaneously interfering sources and background noise are usually modeled by a diffuse noise field. However, in reality, the free-field assumption is very weak because of the reverberant nature of acoustic environments. Therefore, we propose to estimate this simplified MWF solution in each frequency bin separately to cope with reverberation. We show that this approach can very efficiently be realized by the combination of a blocking matrix based on semi-blind source separation ('directional BSS'), which provides a continuously updated reference of all undesired noise and interference components separated from the desired source and its reflections, and a single-channel Wiener postfilter. Moreover, it is shown, how the obtained reference signal of all undesired components can efficiently be used to realize the Wiener postfilter, and at the same time, generalizes well-known postfilter realizations. The proposed front-end and its integration into an automatic speech recognition (ASR) system are analyzed and evaluated in noisy living-room-like environments according to the PASCAL CHiME challenge. A comparison to a simplified front-end based on a free-field assumption shows that the introduced system substantially improves the speech quality and the recognition performance under the considered adverse conditions.}, language = {de} } @article{SehrBarfussHofmannetal., author = {Sehr, Armin and Barfuss, Hendrik and Hofmann, Christian and Maas, Roland and Kellermann, Walter}, title = {Efficient training of acoustic models for reverberation-robust medium-vocabulary automatic speech recognition}, series = {2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA, 12-14 May 2014, Villers-les-Nancy, France}, journal = {2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA, 12-14 May 2014, Villers-les-Nancy, France}, publisher = {IEEE}, doi = {10.1109/HSCMA.2014.6843275}, pages = {177 -- 181}, abstract = {A recently proposed concept for training reverberation-robust acoustic models for automatic speech recognition using pairs of clean and reverberant data is extended from word models to tied-state triphone models in this paper. The key idea of the concept, termed ICEWIND, is to use the clean data for the temporal alignment and the reverberant data for the estimation of the emission densities. Experiments with the 5000-word Wall Street Journal corpus confirm the benefits of ICEWIND with tied-state triphones: While the training time is reduced by more than 90\%, the word accuracy is improved at the same time, both for room-specific and multi-style hidden Markov models. Since the acoustic models trained with ICEWIND need less Gaussian components for the emission densities to achieve comparable recognition rates as Baum-Welch acoustic models, ICEWIND also allows for a reduced decoding complexity.}, language = {en} } @inproceedings{YoshiokaSehrDelcroixetal., author = {Yoshioka, Takuya and Sehr, Armin and Delcroix, Marc and Kinoshita, Keisuke and Maas, Roland and Nakatani, Tomohiro and Kellermann, Walter}, title = {Survey on approaches to speech recognition in reverberant environments}, series = {Asia-Pacific Signal \& Information Processing Association annual summit and conference (APSIPA ASC), 2012 : Hollywood, California, USA, 3 - 6 Dec. 2012}, booktitle = {Asia-Pacific Signal \& Information Processing Association annual summit and conference (APSIPA ASC), 2012 : Hollywood, California, USA, 3 - 6 Dec. 2012}, publisher = {IEEE}, isbn = {978-0-6157-0050-2}, abstract = {This paper overviews the state of the art in reverberant speech processing from the speech recognition viewpoint. First, it points out that the key to successful reverberant speech recognition is to account for long-term dependencies between reverberant observations obtained from consecutive time frames. Then, a diversity of approaches that exploit the long-term dependencies in various ways is described, ranging from signal and feature dereverberation to acoustic model compensation tailored to reverberation. A framework for classifying those approaches is presented to highlight similarities and differences between them.}, language = {en} } @inproceedings{SehrYoshiokaDelcroixetal., author = {Sehr, Armin and Yoshioka, Takuya and Delcroix, Marc and Kinoshita, Keisuke and Nakatani, Tomohiro and Maas, Roland and Kellermann, Walter}, title = {Conditional emission densities for combining speech enhancement and recognition systems}, series = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 25 - 29 August 2013, Lyon, France}, booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 25 - 29 August 2013, Lyon, France}, publisher = {ISCA}, doi = {10.21437/Interspeech.2013-265}, pages = {3502 -- 3506}, abstract = {A novel framework based on conditional emission densities for hidden Markov models (HMMs) is proposed in this contribution to integrate speech enhancement systems with automatic speech recognition systems. In the training phase, the observed feature vectors, corrupted by background noise and reverberation, together with estimates for the interference as provided by the speech enhancement system are used for training joint densities of the observations and the interference estimates. In the decoding phase, the joint densities are transformed to conditional densities of the observed features given the interference estimates. Thus, front end processing can be exploited for obtaining interference estimates, and the estimation errors can be modeled very effectively in a data-driven way. Connected digit recognition experiments in a simulated reverberant environment show the potential of the proposed approach: HMMs with the proposed conditional densities outperform various configurations of conventional HMMs in the logarithmic melspectral domain. This is a first step towards using conditional densities for creating synergies between front end and back end. Index Terms: speech enhancement, robust speech recognition, dereverberation, conditional HMM emission densities, frame- by-frame model adaptation.}, language = {en} }