@inproceedings{12900, abstract = {{Deep attractor networks (DANs) are a recently introduced method to blindly separate sources from spectral features of a monaural recording using bidirectional long short-term memory networks (BLSTMs). Due to the nature of BLSTMs, this is inherently not online-ready and resorting to operating on blocks yields a block permutation problem in that the index of each speaker may change between blocks. We here propose the joint modeling of spatial and spectral features to solve the block permutation problem and generalize DANs to multi-channel meeting recordings: The DAN acts as a spectral feature extractor for a subsequent model-based clustering approach. We first analyze different joint models in batch-processing scenarios and finally propose a block-online blind source separation algorithm. The efficacy of the proposed models is demonstrated on reverberant mixtures corrupted by real recordings of multi-channel background noise. We demonstrate that both the proposed batch-processing and the proposed block-online system outperform (a) a spatial-only model with a state-of-the-art frequency permutation solver and (b) a spectral-only model with an oracle block permutation solver in terms of signal to distortion ratio (SDR) gains.}}, author = {{Drude, Lukas and Higuchi,, Takuya and Kinoshita, Keisuke and Nakatani, Tomohiro and Haeb-Umbach, Reinhold}}, booktitle = {{ICASSP 2018, Calgary, Canada}}, title = {{{Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online Blind Source Separation}}}, year = {{2018}}, } @inproceedings{12901, abstract = {{This work examines acoustic beamformers employing neural networks (NNs) for mask prediction as front-end for automatic speech recognition (ASR) systems for practical scenarios like voice-enabled home devices. To test the versatility of the mask predicting network, the system is evaluated with different recording hardware, different microphone array designs, and different acoustic models of the downstream ASR system. Significant gains in recognition accuracy are obtained in all configurations despite the fact that the NN had been trained on mismatched data. Unlike previous work, the NN is trained on a feature level objective, which gives some performance advantage over a mask related criterion. Furthermore, different approaches for realizing online, or adaptive, NN-based beamforming are explored, where the online algorithms still show significant gains compared to the baseline performance.}}, author = {{Boeddeker, Christoph and Erdogan, Hakan and Yoshioka, Takuya and Haeb-Umbach, Reinhold}}, booktitle = {{ICASSP 2018, Calgary, Canada}}, title = {{{Exploring Practical Aspects of Neural Mask-Based Beamforming for Far-Field Speech Recognition}}}, year = {{2018}}, } @inproceedings{12899, abstract = {{This contribution presents a speech enhancement system for the CHiME-5 Dinner Party Scenario. The front-end employs multi-channel linear time-variant filtering and achieves its gains without the use of a neural network. We present an adaptation of blind source separation techniques to the CHiME-5 database which we call Guided Source Separation (GSS). Using the baseline acoustic and language model, the combination of Weighted Prediction Error based dereverberation, guided source separation, and beamforming reduces the WER by 10:54% (relative) for the single array track and by 21:12% (relative) on the multiple array track.}}, author = {{Boeddeker, Christoph and Heitkaemper, Jens and Schmalenstroeer, Joerg and Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments, Hyderabad, India}}, title = {{{Front-End Processing for the CHiME-5 Dinner Party Scenario}}}, year = {{2018}}, } @inproceedings{6859, abstract = {{Signal processing in WASNs is based on a software framework for hosting the algorithms as well as on a set of wireless connected devices representing the hardware. Each of the nodes contributes memory, processing power, communication bandwidth and some sensor information for the tasks to be solved on the network. In this paper we present our MARVELO framework for distributed signal processing. It is intended for transforming existing centralized implementations into distributed versions. To this end, the software only needs a block-oriented implementation, which MARVELO picks-up and distributes on the network. Additionally, our sensor node hardware and the audio interfaces responsible for multi-channel recordings are presented.}}, author = {{Afifi, Haitham and Schmalenstroeer, Joerg and Ullmann, Joerg and Haeb-Umbach, Reinhold and Karl, Holger}}, booktitle = {{Speech Communication; 13th ITG-Symposium}}, pages = {{1--5}}, title = {{{MARVELO - A Framework for Signal Processing in Wireless Acoustic Sensor Networks}}}, year = {{2018}}, } @inproceedings{11747, abstract = {{In this paper, we present a neural network based classification algorithm for the discrimination of moving from stationary targets in the sight of an automotive radar sensor. Compared to existing algorithms, the proposed algorithm can take into account multiple local radar targets instead of performing classification inference on each target individually resulting in superior discrimination accuracy, especially suitable for non rigid objects, like pedestrians, which in general have a wide velocity spread when multiple targets are detected.}}, author = {{Grimm, Christopher and Breddermann, Tobias and Farhoud, Ridha and Fei, Tai and Warsitz, Ernst and Haeb-Umbach, Reinhold}}, booktitle = {{International Conference on Microwaves for Intelligent Mobility (ICMIM) 2018}}, title = {{{Discrimination of Stationary from Moving Targets with Recurrent Neural Networks in Automotive Radar}}}, year = {{2018}}, } @inproceedings{11907, abstract = {{The invention of the Variational Autoencoder enables the application of Neural Networks to a wide range of tasks in unsupervised learning, including the field of Acoustic Unit Discovery (AUD). The recently proposed Hidden Markov Model Variational Autoencoder (HMMVAE) allows a joint training of a neural network based feature extractor and a structured prior for the latent space given by a Hidden Markov Model. It has been shown that the HMMVAE significantly outperforms pure GMM-HMM based systems on the AUD task. However, the HMMVAE cannot autonomously infer the number of acoustic units and thus relies on the GMM-HMM system for initialization. This paper introduces the Bayesian Hidden Markov Model Variational Autoencoder (BHMMVAE) which solves these issues by embedding the HMMVAE in a Bayesian framework with a Dirichlet Process Prior for the distribution of the acoustic units, and diagonal or full-covariance Gaussians as emission distributions. Experiments on TIMIT and Xitsonga show that the BHMMVAE is able to autonomously infer a reasonable number of acoustic units, can be initialized without supervision by a GMM-HMM system, achieves computationally efficient stochastic variational inference by using natural gradient descent, and, additionally, improves the AUD performance over the HMMVAE.}}, author = {{Glarner, Thomas and Hanebrink, Patrick and Ebbers, Janek and Haeb-Umbach, Reinhold}}, booktitle = {{INTERSPEECH 2018, Hyderabad, India}}, title = {{{Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery}}}, year = {{2018}}, } @inproceedings{11838, abstract = {{Distributed sensor data acquisition usually encompasses data sampling by the individual devices, where each of them has its own oscillator driving the local sampling process, resulting in slightly different sampling rates at the individual sensor nodes. Nevertheless, for certain downstream signal processing tasks it is important to compensate even for small sampling rate offsets. Aligning the sampling rates of oscillators which differ only by a few parts-per-million, is, however, challenging and quite different from traditional multirate signal processing tasks. In this paper we propose to transfer a precise but computationally demanding time domain approach, inspired by the Nyquist-Shannon sampling theorem, to an efficient frequency domain implementation. To this end a buffer control is employed which compensates for sampling offsets which are multiples of the sampling period, while a digital filter, realized by the wellknown Overlap-Save method, handles the fractional part of the sampling phase offset. With experiments on artificially misaligned data we investigate the parametrization, the efficiency, and the induced distortions of the proposed resampling method. It is shown that a favorable compromise between residual distortion and computational complexity is achieved, compared to other sampling rate offset compensation techniques.}}, author = {{Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{26th European Signal Processing Conference (EUSIPCO 2018)}}, title = {{{Efficient Sampling Rate Offset Compensation - An Overlap-Save Based Approach}}}, year = {{2018}}, } @inproceedings{11876, abstract = {{This paper describes the systems for the single-array track and the multiple-array track of the 5th CHiME Challenge. The final system is a combination of multiple systems, using Confusion Network Combination (CNC). The different systems presented here are utilizing different front-ends and training sets for a Bidirectional Long Short-Term Memory (BLSTM) Acoustic Model (AM). The front-end was replaced by enhancements provided by Paderborn University [1]. The back-end has been implemented using RASR [2] and RETURNN [3]. Additionally, a system combination including the hypothesis word graphs from the system of the submission [1] has been performed, which results in the final best system.}}, author = {{Kitza, Markus and Michel, Wilfried and Boeddeker, Christoph and Heitkaemper, Jens and Menne, Tobias and Schlüter, Ralf and Ney, Hermann and Schmalenstroeer, Joerg and Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments, Hyderabad, India}}, title = {{{The RWTH/UPB System Combination for the CHiME 2018 Workshop}}}, year = {{2018}}, } @inproceedings{11836, abstract = {{Due to their distributed nature wireless acoustic sensor networks offer great potential for improved signal acquisition, processing and classification for applications such as monitoring and surveillance, home automation, or hands-free telecommunication. To reduce the communication demand with a central server and to raise the privacy level it is desirable to perform processing at node level. The limited processing and memory capabilities on a sensor node, however, stand in contrast to the compute and memory intensive deep learning algorithms used in modern speech and audio processing. In this work, we perform benchmarking of commonly used convolutional and recurrent neural network architectures on a Raspberry Pi based acoustic sensor node. We show that it is possible to run medium-sized neural network topologies used for speech enhancement and speech recognition in real time. For acoustic event recognition, where predictions in a lower temporal resolution are sufficient, it is even possible to run current state-of-the-art deep convolutional models with a real-time-factor of 0:11.}}, author = {{Ebbers, Janek and Heitkaemper, Jens and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{ITG 2018, Oldenburg, Germany}}, title = {{{Benchmarking Neural Network Architectures for Acoustic Sensor Networks}}}, year = {{2018}}, } @inproceedings{11839, abstract = {{It has been experimentally verified that sampling rate offsets (SROs) between the input channels of an acoustic beamformer have a detrimental effect on the achievable SNR gains. In this paper we derive an analytic model to study the impact of SRO on the estimation of the spatial noise covariance matrix used in MVDR beamforming. It is shown that a perfect compensation of the SRO is impossible if the noise covariance matrix is estimated by time averaging, even if the SRO is perfectly known. The SRO should therefore be compensated for prior to beamformer coefficient estimation. We present a novel scheme where SRO compensation and beamforming closely interact, saving some computational effort compared to separate SRO adjustment followed by acoustic beamforming.}}, author = {{Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{ITG 2018, Oldenburg, Germany}}, title = {{{Insights into the Interplay of Sampling Rate Offsets and MVDR Beamforming}}}, year = {{2018}}, } @inproceedings{11717, abstract = {{In this work, we address the limited availability of large annotated databases for real-life audio event detection by utilizing the concept of transfer learning. This technique aims to transfer knowledge from a source domain to a target domain, even if source and target have different feature distributions and label sets. We hypothesize that all acoustic events share the same inventory of basic acoustic building blocks and differ only in the temporal order of these acoustic units. We then construct a deep neural network with convolutional layers for extracting the acoustic units and a recurrent layer for capturing the temporal order. Under the above hypothesis, transfer learning from a source to a target domain with a different acoustic event inventory is realized by transferring the convolutional layers from the source to the target domain. The recurrent layer is, however, learnt directly from the target domain. Experiments on the transfer from a synthetic source database to the reallife target database of DCASE 2016 demonstrate that transfer learning leads to improved detection performance on average. However, the successful transfer to detect events which are very different from what was seen in the source domain, could not be verified.}}, author = {{Arora, Prerna and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)}}, title = {{{A Study on Transfer Learning for Acoustic Event Detection in a Real Life Scenario}}}, year = {{2017}}, } @techreport{11735, abstract = {{This report describes the computation of gradients by algorithmic differentiation for statistically optimum beamforming operations. Especially the derivation of complex-valued functions is a key component of this approach. Therefore the real-valued algorithmic differentiation is extended via the complex-valued chain rule. In addition to the basic mathematic operations the derivative of the eigenvalue problem with complex-valued eigenvectors is one of the key results of this report. The potential of this approach is shown with experimental results on the CHiME-3 challenge database. There, the beamforming task is used as a front-end for an ASR system. With the developed derivatives a joint optimization of a speech enhancement and speech recognition system w.r.t. the recognition optimization criterion is possible.}}, author = {{Boeddeker, Christoph and Hanebrink, Patrick and Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}}, title = {{{On the Computation of Complex-valued Gradients with Application to Statistically Optimum Beamforming}}}, year = {{2017}}, } @inproceedings{11736, abstract = {{In this paper we show how a neural network for spectral mask estimation for an acoustic beamformer can be optimized by algorithmic differentiation. Using the beamformer output SNR as the objective function to maximize, the gradient is propagated through the beamformer all the way to the neural network which provides the clean speech and noise masks from which the beamformer coefficients are estimated by eigenvalue decomposition. A key theoretical result is the derivative of an eigenvalue problem involving complex-valued eigenvectors. Experimental results on the CHiME-3 challenge database demonstrate the effectiveness of the approach. The tools developed in this paper are a key component for an end-to-end optimization of speech enhancement and speech recognition.}}, author = {{Boeddeker, Christoph and Hanebrink, Patrick and Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)}}, title = {{{Optimizing Neural-Network Supported Acoustic Beamforming by Algorithmic Differentiation}}}, year = {{2017}}, } @inproceedings{11737, abstract = {{The benefits of both a logarithmic spectral amplitude (LSA) estimation and a modeling in a generalized spectral domain (where short-time amplitudes are raised to a generalized power exponent, not restricted to magnitude or power spectrum) are combined in this contribution to achieve a better tradeoff between speech quality and noise suppression in single-channel speech enhancement. A novel gain function is derived to enhance the logarithmic generalized spectral amplitudes of noisy speech. Experiments on the CHiME-3 dataset show that it outperforms the famous minimum mean squared error (MMSE) LSA gain function of Ephraim and Malah in terms of noise suppression by 1.4 dB, while the good speech quality of the MMSE-LSA estimator is maintained.}}, author = {{Chinaev, Alleksej and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)}}, title = {{{A Generalized Log-Spectral Amplitude Estimator for Single-Channel Speech Enhancement}}}, year = {{2017}}, } @inproceedings{11754, abstract = {{Recent advances in discriminatively trained mask estimation networks to extract a single source utilizing beamforming techniques demonstrate, that the integration of statistical models and deep neural networks (DNNs) are a promising approach for robust automatic speech recognition (ASR) applications. In this contribution we demonstrate how discriminatively trained embeddings on spectral features can be tightly integrated into statistical model-based source separation to separate and transcribe overlapping speech. Good generalization to unseen spatial configurations is achieved by estimating a statistical model at test time, while still leveraging discriminative training of deep clustering embeddings on a separate training set. We formulate an expectation maximization (EM) algorithm which jointly estimates a model for deep clustering embeddings and complex-valued spatial observations in the short time Fourier transform (STFT) domain at test time. Extensive simulations confirm, that the integrated model outperforms (a) a deep clustering model with a subsequent beamforming step and (b) an EM-based model with a beamforming step alone in terms of signal to distortion ratio (SDR) and perceptually motivated metric (PESQ) gains. ASR results on a reverberated dataset further show, that the aforementioned gains translate to reduced word error rates (WERs) even in reverberant environments.}}, author = {{Drude, Lukas and Haeb-Umbach, Reinhold}}, booktitle = {{INTERSPEECH 2017, Stockholm, Schweden}}, title = {{{Tight integration of spatial and spectral features for BSS with Deep Clustering embeddings}}}, year = {{2017}}, } @inproceedings{11770, abstract = {{In this contribution we show how to exploit text data to support word discovery from audio input in an underresourced target language. Given audio, of which a certain amount is transcribed at the word level, and additional unrelated text data, the approach is able to learn a probabilistic mapping from acoustic units to characters and utilize it to segment the audio data into words without the need of a pronunciation dictionary. This is achieved by three components: an unsupervised acoustic unit discovery system, a supervisedly trained acoustic unit-to-grapheme converter, and a word discovery system, which is initialized with a language model trained on the text data. Experiments for multiple setups show that the initialization of the language model with text data improves the word segementation performance by a large margin.}}, author = {{Glarner, Thomas and Boenninghoff, Benedikt and Walter, Oliver and Haeb-Umbach, Reinhold}}, booktitle = {{INTERSPEECH 2017, Stockholm, Schweden}}, title = {{{Leveraging Text Data for Word Segmentation for Underresourced Languages}}}, year = {{2017}}, } @inproceedings{11809, abstract = {{This paper presents an end-to-end training approach for a beamformer-supported multi-channel ASR system. A neural network which estimates masks for a statistically optimum beamformer is jointly trained with a network for acoustic modeling. To update its parameters, we propagate the gradients from the acoustic model all the way through feature extraction and the complex valued beamforming operation. Besides avoiding a mismatch between the front-end and the back-end, this approach also eliminates the need for stereo data, i.e., the parallel availability of clean and noisy versions of the signals. Instead, it can be trained with real noisy multichannel data only. Also, relying on the signal statistics for beamforming, the approach makes no assumptions on the configuration of the microphone array. We further observe a performance gain through joint training in terms of word error rate in an evaluation of the system on the CHiME 4 dataset.}}, author = {{Heymann, Jahn and Drude, Lukas and Boeddeker, Christoph and Hanebrink, Patrick and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)}}, title = {{{BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System}}}, year = {{2017}}, } @article{11811, abstract = {{Acoustic beamforming can greatly improve the performance of Automatic Speech Recognition (ASR) and speech enhancement systems when multiple channels are available. We recently proposed a way to support the model-based Generalized Eigenvalue beamforming operation with a powerful neural network for spectral mask estimation. The enhancement system has a number of desirable properties. In particular, neither assumptions need to be made about the nature of the acoustic transfer function (e.g., being anechonic), nor does the array configuration need to be known. While the system has been originally developed to enhance speech in noisy environments, we show in this article that it is also effective in suppressing reverberation, thus leading to a generic trainable multi-channel speech enhancement system for robust speech processing. To support this claim, we consider two distinct datasets: The CHiME 3 challenge, which features challenging real-world noise distortions, and the Reverb challenge, which focuses on distortions caused by reverberation. We evaluate the system both with respect to a speech enhancement and a recognition task. For the first task we propose a new way to cope with the distortions introduced by the Generalized Eigenvalue beamformer by renormalizing the target energy for each frequency bin, and measure its effectiveness in terms of the PESQ score. For the latter we feed the enhanced signal to a strong DNN back-end and achieve state-of-the-art ASR results on both datasets. We further experiment with different network architectures for spectral mask estimation: One small feed-forward network with only one hidden layer, one Convolutional Neural Network and one bi-directional Long Short-Term Memory network, showing that even a small network is capable of delivering significant performance improvements.}}, author = {{Heymann, Jahn and Drude, Lukas and Haeb-Umbach, Reinhold}}, journal = {{Computer Speech and Language}}, title = {{{A Generic Neural Acoustic Beamforming Architecture for Robust Multi-Channel Speech Processing}}}, year = {{2017}}, } @inproceedings{11763, abstract = {{In this paper, we apply a high-resolution approach, i.e. the matrix pencil method (MPM), to the FMCW automotive radar system to separate the neighboring targets, which share similar parameters, i.e. range, relative speed and azimuth angle, and cause overlapping in the radar spectrum. In order to adapt the 1D model of MPM to the 2D range-velocity spectrum and simultaneously limit the computational cost, some preprocessing steps are proposed to construct a novel separation algorithm. Finally, this algorithm is evaluated in both simulation and real data, and the results indicate a promising performance.}}, author = {{Fei, Tai and Grimm, Christopher and Farhoud, Ridha and Breddermann, Tobias and Warsitz, Ernst and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE International conference on microwave, communications, anthenas and electronic systems}}, title = {{{A Novel Target Separation Algorithm Applied to The Two-Dimensional Spectrum for FMCW Automotive Radar Systems}}}, year = {{2017}}, } @inproceedings{11772, abstract = {{In this paper, we present a hypothesis test for the classification of moving targets in the sight of an automotive radar sensor. For this purpose, a statistical model of the relative velocity between a stationary target and the radar sensor has been developed. With respect to the statistical properties a confidence interval is calculated and targets with relative velocity lying outside this interval are classified as moving targets. Compared to existing algorithms our approach is able to give robust classification independent of the number of observed moving targets and is characterized by an instantaneous classification, a simple parameterization of the model and an automatic calculation of the discriminating threshold.}}, author = {{Grimm, Christopher and Breddermann, Tobias and Farhoud, Ridha and Fei, Tai and Warsitz, Ernst and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE International conference on microwave, communications, anthenas and electronic systems (COMCAS)}}, title = {{{Hypothesis Test for the Detection of Moving Targets in Automotive Radar}}}, year = {{2017}}, }