@inproceedings{11895, abstract = {{Multi-channel speech enhancement algorithms rely on a synchronous sampling of the microphone signals. This, however, cannot always be guaranteed, especially if the sensors are distributed in an environment. To avoid performance degradation the sampling rate offset needs to be estimated and compensated for. In this contribution we extend the recently proposed coherence drift based method in two important directions. First, the increasing phase shift in the short-time Fourier transform domain is estimated from the coherence drift in a Matched Filterlike fashion, where intermediate estimates are weighted by their instantaneous SNR. Second, an observed bias is removed by iterating between offset estimation and compensation by resampling a couple of times. The effectiveness of the proposed method is demonstrated by speech recognition results on the output of a beamformer with and without sampling rate offset compensation between the input channels. We compare MVDR and maximum-SNR beamformers in reverberant environments and further show that both benefit from a novel phase normalization, which we also propose in this contribution.}}, author = {{Schmalenstroeer, Joerg and Heymann, Jahn and Drude, Lukas and Boeddeker, Christoph and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)}}, title = {{{Multi-Stage Coherence Drift Based Sampling Rate Synchronization for Acoustic Beamforming}}}, year = {{2017}}, } @inproceedings{11890, abstract = {{In this paper we study the influence of directional radio patterns of Bluetooth low energy (BLE) beacons on smartphone localization accuracy and beacon network planning. A two-dimensional model of the power emission characteristic is derived from measurements of the radiation pattern of BLE beacons carried out in an RF chamber. The Cramer-Rao lower bound (CRLB) for position estimation is then derived for this directional power emission model. With this lower bound on the RMS positioning error the coverage of different beacon network configurations can be evaluated. For near-optimal network planing an evolutionary optimization algorithm for finding the best beacon placement is presented.}}, author = {{Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{24th European Signal Processing Conference (EUSIPCO 2016)}}, title = {{{Investigations into Bluetooth Low Energy Localization Precision Limits}}}, year = {{2016}}, } @inproceedings{11874, author = {{Hoang, Manh Kha and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{40th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015)}}, title = {{{Aligning training models with smartphone properties in WiFi fingerprinting based indoor localization}}}, year = {{2015}}, } @article{11898, abstract = {{Abstract In this paper we present an approach for synchronizing a wireless acoustic sensor network using a two-stage procedure. First the clock frequency and phase differences between pairs of nodes are estimated employing a two-way message exchange protocol. The estimates are further improved in a Kalman filter with a dedicated observation error model. In the second stage network-wide synchronization is achieved by means of a gossiping algorithm which estimates the average clock frequency and phase of the sensor nodes. These averages are viewed as frequency and phase of a virtual master clock, to which the clocks of the sensor nodes have to be adjusted. The amount of adjustment is computed in a specific control loop. While these steps are done in software, the actual sampling rate correction is carried out in hardware by using an adjustable frequency synthesizer. Experimental results obtained from hardware devices and software simulations of large scale networks are presented.}}, author = {{Schmalenstroeer, Joerg and Jebramcik, Patrick and Haeb-Umbach, Reinhold}}, issn = {{0165-1684}}, journal = {{Signal Processing}}, keywords = {{Gossip algorithm}}, pages = {{ -- }}, title = {{{A combined hardware-software approach for acoustic sensor network synchronization }}}, doi = {{http://dx.doi.org/10.1016/j.sigpro.2014.06.030}}, year = {{2014}}, } @inproceedings{11897, abstract = {{ "In this paper we present an approach for synchronizing the sampling clocks of distributed microphones over a wireless network. The proposed system uses a two stage procedure. It first employs a two-way message exchange algorithm to estimate the clock phase and frequency difference between two nodes and then uses a gossiping algorithmto estimate a virtual master clock, to which all sensor nodes synchronize. Simulation results are presented for networks of different topology and size, showing the effectiveness of our approach." }}, author = {{Schmalenstroeer, Joerg and Jebramcik, Patrick and Haeb-Umbach, Reinhold}}, booktitle = {{39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)}}, title = {{{A Gossiping Approach to Sampling Clock Synchronization in Wireless Acoustic Sensor Networks}}}, year = {{2014}}, } @inproceedings{11903, abstract = {{"Acoustic sensor network clock synchronization via time stamp exchange between the sensor nodes is not accurate enough for many acoustic signal processing tasks, such as speaker localization. To improve synchronization accuracy it has therefore been proposed to employ a Kalman Filter to obtain improved frequency deviation and phase offset estimates. The estimation requires a statistical model of the errors of the measurements obtained from the time stamp exchange algorithm. These errors are caused by random transmission delays and hardware effects and are thus network specific. In this contribution we develop an algorithm to estimate the parameters of the measurement error model alongside the Kalman filter based sampling clock synchronization, employing the Expectation Maximization algorithm. Simulation results demonstrate that the online estimation of the error model parameters leads only to a small degradation of the synchronization performance compared to a perfectly known observation error model."}}, author = {{Schmalenstroeer, Joerg and Zhao, Weile and Haeb-Umbach, Reinhold}}, booktitle = {{11. ITG Fachtagung Sprachkommunikation (ITG 2014)}}, title = {{{Online Observation Error Model Estimation for Acoustic Sensor Network Synchronization}}}, year = {{2014}}, } @techreport{11926, abstract = {{In this paper we present a novel initialization method for unsupervised learning of acoustic patterns in recordings of continuous speech. The pattern discovery task is solved by dynamic time warping whose performance we improve by a smart starting point selection. This enables a more accurate discovery of patterns compared to conventional approaches. After graph-based clustering the patterns are employed for training hidden Markov models for an unsupervised speech acquisition. By iterating between model training and decoding in an EM-like framework the word accuracy is continuously improved. On the TIDIGITS corpus we achieve a word error rate of about 13 percent by the proposed unsupervised pattern discovery approach, which neither assumes knowledge of the acoustic units nor of the labels of the training data.}}, author = {{Walter, Oliver and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, title = {{{A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)}}}, 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}}, } @inproceedings{11891, abstract = {{In this paper we present a combined hardware/software approach for synchronizing the sampling clocks of an acoustic sensor network. A first clock frequency offset estimate is obtained by a time stamp exchange protocol with a low data rate and computational requirements. The estimate is then postprocessed by a Kalman filter which exploits the specific properties of the statistics of the frequency offset estimation error. In long term experiments the deviation between the sampling oscillators of two sensor nodes never exceeded half a sample with a wired and with a wireless link between the nodes. The achieved precision enables the estimation of time difference of arrival values across different hardware devices without sharing a common sampling hardware.}}, author = {{Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{21th European Signal Processing Conference (EUSIPCO 2013)}}, keywords = {{synchronization, acoustic sensor network}}, title = {{{Sampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model}}}, year = {{2013}}, } @inproceedings{11818, abstract = {{In this paper we present a system for indoor navigation based on received signal strength index information of Wireless-LAN access points and relative position estimates. The relative position information is gathered from inertial smartphone sensors using a step detection and an orientation estimate. Our map data is hosted on a server employing a map renderer and a SQL database. The database includes a complete multilevel office building, within which the user can navigate. During navigation, the client retrieves the position estimate from the server, together with the corresponding map tiles to visualize the user's position on the smartphone display.}}, author = {{Hoang, Manh Kha and Schmitz, Sarah and Drueke, Christian and Vu, Dang Hai Tran and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{Positioning Navigation and Communication (WPNC), 2013 10th Workshop on}}, keywords = {{SQL, navigation, smart phones, wireless LAN, RSSI, SQL database, complete multilevel office building, inertial sensor information, inertial smartphone sensors, map renderer, received signal strength index information, relative position estimates, server based indoor navigation, step detection, wireless-LAN access points, Smartphone, fingerprint, indoor navigation, map tile}}, pages = {{1--6}}, title = {{{Server based indoor navigation using RSSI and inertial sensor information}}}, doi = {{10.1109/WPNC.2013.6533263}}, year = {{2013}}, } @inproceedings{11817, abstract = {{In this paper we present a modified hidden Markov model (HMM) for the fusion of received signal strength index (RSSI) information of WiFi access points and relative position information which is obtained from the inertial sensors of a smartphone for indoor positioning. Since the states of the HMM represent the potential user locations, their number determines the quantization error introduced by discretizing the allowable user positions through the use of the HMM. To reduce this quantization error we introduce â??pseudoâ?? states, whose emission probability, which models the RSSI measurements at this location, is synthesized from those of the neighboring states of which a Gaussian emission probability has been estimated during the training phase. The experimental results demonstrate the effectiveness of this approach. By introducing on average two pseudo states per original HMM state the positioning error could be significantly reduced without increasing the training effort.}}, author = {{Hoang, Manh Kha and Schmalenstroeer, Joerg and Drueke, Christian and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}}, booktitle = {{21th European Signal Processing Conference (EUSIPCO 2013)}}, title = {{{A Hidden Markov Model for Indoor User Tracking Based on WiFi Fingerprinting and Step Detection}}}, year = {{2013}}, } @inproceedings{11833, abstract = {{In this paper we propose an approach to retrieve the geometry of an acoustic sensor network consisting of spatially distributed microphone arrays from unconstrained speech input. The calibration relies on Direction of Arrival (DoA) measurements which do not require a clock synchronization among the sensor nodes. The calibration problem is formulated as a cost function optimization task, which minimizes the squared differences between measured and predicted observations and additionally avoids the existence of minima that correspond to mirrored versions of the actual sensor orientations. Further, outlier measurements caused by reverberation are mitigated by a Random Sample Consensus (RANSAC) approach. The experimental results show a mean positioning error of at most 25 cm even in highly reverberant environments.}}, author = {{Jacob, Florian and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{International Workshop on Acoustic Signal Enhancement (IWAENC 2012)}}, keywords = {{Unsupervised, geometry calibration, microphone arrays, position self-calibration}}, title = {{{Microphone Array Position Self-Calibration from Reverberant Speech Input}}}, year = {{2012}}, } @inproceedings{11925, abstract = {{In this paper we present a system for car navigation by fusing sensor data on an Android smartphone. The key idea is to use both the internal sensors of the smartphone (e.g., gyroscope) and sensor data from the car (e.g., speed information) to support navigation via GPS. To this end we employ a CAN-Bus-to-Bluetooth adapter to establish a wireless connection between the smartphone and the CAN-Bus of the car. On the smartphone a strapdown algorithm and an error-state Kalman filter are used to fuse the different sensor data streams. The experimental results show that the system is able to maintain higher positioning accuracy during GPS dropouts, thus improving the availability and reliability, compared to GPS-only solutions.}}, author = {{Walter, Oliver and Schmalenstroeer, Joerg and Engler, Andreas and Haeb-Umbach, Reinhold}}, booktitle = {{9th Workshop on Positioning Navigation and Communication (WPNC 2012)}}, keywords = {{Smartphone, navigation, sensor fusion}}, title = {{{Smartphone-Based Sensor Fusion for Improved Vehicular Navigation}}}, year = {{2012}}, } @inproceedings{11889, abstract = {{In this paper we propose to jointly consider Segmental Dynamic Time Warping and distance clustering for the unsupervised learning of acoustic events. As a result, the computational complexity increases only linearly with the dababase size compared to a quadratic increase in a sequential setup, where all pairwise SDTW distances between segments are computed prior to clustering. Further, we discuss options for seed value selection for clustering and show that drawing seeds with a probability proportional to the distance from the already drawn seeds, known as K-means++ clustering, results in a significantly higher probability of finding representatives of each of the underlying classes, compared to the commonly used draws from a uniform distribution. Experiments are performed on an acoustic event classification and an isolated digit recognition task, where on the latter the final word accuracy approaches that of supervised training.}}, author = {{Schmalenstroeer, Joerg and Bartek, Markus and Haeb-Umbach, Reinhold}}, booktitle = {{Interspeech 2011}}, title = {{{Unsupervised learning of acoustic events using dynamic time warping and hierarchical K-means++ clustering}}}, year = {{2011}}, } @inproceedings{11896, abstract = {{In this paper we propose a procedure for estimating the geometric configuration of an arbitrary acoustic sensor placement. It determines the position and the orientation of microphone arrays in 2D while locating a source by direction-of-arrival (DoA) estimation. Neither artificial calibration signals nor unnatural user activity are required. The problem of scale indeterminacy inherent to DoA-only observations is solved by adding time difference of arrival (TDOA) measurements. The geometry calibration method is numerically stable and delivers precise results in moderately reverberated rooms. Simulation results are confirmed by laboratory experiments.}}, author = {{Schmalenstroeer, Joerg and Jacob, Florian and Haeb-Umbach, Reinhold and Hennecke, Marius and Fink, Gernot A.}}, booktitle = {{Interspeech 2011}}, title = {{{Unsupervised Geometry Calibration of Acoustic Sensor Networks Using Source Correspondences}}}, year = {{2011}}, } @inproceedings{9456, abstract = {{In this paper we present our experimental results about classifying audio data into broad acoustic categories. The reverberated sound samples from indoor recordings are grouped into four classes, namely speech, music, acoustic events and noise. We investigated a total of 188 acoustic features and achieved for the best configuration a classification accuracy better than 98\%. This was achieved by a 42-dimensional feature vector consisting of Mel-Frequency Cepstral Coefficients, an autocorrelation feature and so-called track features that measure the length of ''traces'' of high energy in the spectrogram. We also found a 4-feature configuration with a classification rate of about 90\% allowing for broad acoustic category classification with low computational effort.}}, author = {{Schmalenstroeer, Joerg and Bartek, Markus and Haeb-Umbach, Reinhold}}, booktitle = {{37. Deutsche Jahrestagung fuer Akustik (DAGA 2011)}}, title = {{{Investigations into Features for Robust Classification into Broad Acoustic Categories}}}, year = {{2011}}, } @article{11892, abstract = {{For an environment to be perceived as being smart, contextual information has to be gathered to adapt the system's behavior and its interface towards the user. Being a rich source of context information speech can be acquired unobtrusively by microphone arrays and then processed to extract information about the user and his environment. In this paper, a system for joint temporal segmentation, speaker localization, and identification is presented, which is supported by face identification from video data obtained from a steerable camera. Special attention is paid to latency aspects and online processing capabilities, as they are important for the application under investigation, namely ambient communication. It describes the vision of terminal-less, session-less and multi-modal telecommunication with remote partners, where the user can move freely within his home while the communication follows him. The speaker diarization serves as a context source, which has been integrated in a service-oriented middleware architecture and provided to the application to select the most appropriate I/O device and to steer the camera towards the speaker during ambient communication.}}, author = {{Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, journal = {{IEEE Journal of Selected Topics in Signal Processing}}, keywords = {{audio streaming, audio visual data streaming, context information speech, face identification, face recognition, image segmentation, middleware, multimodal telecommunication, online diarization, service oriented middleware architecture, sessionless telecommunication, software architecture, speaker identification, speaker localization, speaker recognition, steerable camera, telecommunication computing, temporal segmentation, terminal-less telecommunication, video streaming}}, number = {{5}}, pages = {{845--856}}, title = {{{Online Diarization of Streaming Audio-Visual Data for Smart Environments}}}, doi = {{10.1109/JSTSP.2010.2050519}}, volume = {{4}}, year = {{2010}}, } @inproceedings{11900, author = {{Schmalenstroeer, Joerg and Leutnant, Volker and Haeb-Umbach, Reinhold}}, booktitle = {{1st International Workshop on Distributed Computing in Ambient Environments within 32nd Annual Conference on Artificial Intelligence}}, title = {{{Audio-Visual Data Processing for Ambient Communication}}}, year = {{2009}}, } @inproceedings{11806, abstract = {{Microphone arrays represent the basis for many challenging acoustic sensing tasks. The accuracy of techniques like beamforming directly depends on a precise knowledge of the relative positions of the sensors used. Unfortunately, for certain use cases manually measuring the geometry of an array is not feasible due to practical constraints. In this paper we present an approach to unsupervised shape calibration of microphone array networks. We developed a hierarchical procedure that first performs local shape calibration based on coherence analysis and then employs SRP-PHAT in a network calibration method. Practical experiments demonstrate the effectiveness of our approach especially for highly reverberant acoustic environments.}}, author = {{Hennecke, Marius and Ploetz, Thomas and Fink, Gernot A. and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE/SP 15th Workshop on Statistical Signal Processing (SSP 2009)}}, keywords = {{acoustic sensing tasks, array geometry, calibration, coherence analysis, hierarchical procedure, local shape calibration, microphone array networks, microphone arrays, network calibration method, sensor arrays, SRP-PHAT, unsupervised shape calibration}}, pages = {{257--260}}, title = {{{A hierarchical approach to unsupervised shape calibration of microphone array networks}}}, doi = {{10.1109/SSP.2009.5278589}}, year = {{2009}}, } @inproceedings{11899, abstract = {{In this paper we present a system for identifying and localizingspeakers using distant microphone arrays and a steerablepan-tilt-zoom camera. Audio and video streams are processedin real-time to obtain the diarization information {grqq}who speakswhen and where'' with low latency to be used in advanced videoconferencing systems or user-adaptive interfaces. A key featureof the proposed system is to first glean information about thespeaker{\rq}s location and identity from the audio and visual datastreams separately and then to fuse these data in a probabilisticframework employing the Viterbi algorithm. Here, visual evidenceof a person is utilized through a priori state probabilities,while location and speaker change information are employedvia time-variant transition probablities. Experiments show thatvideo information yields a substantial improvement comparedto pure audio-based diarization.}}, author = {{Schmalenstroeer, Joerg and Kelling, Martin and Leutnant, Volker and Haeb-Umbach, Reinhold}}, booktitle = {{Interspeech 2009}}, title = {{{Fusing Audio and Video Information for Online Speaker Diarization}}}, year = {{2009}}, }