@inproceedings{11815, author = {{Heymann, Jahn and Walter, Oliver and Haeb-Umbach, Reinhold and Raj, Bhiksha}}, booktitle = {{Automatic Speech Recognition and Understanding Workshop (ASRU 2013)}}, title = {{{Unsupervised Word Segmentation from Noisy Input}}}, year = {{2013}}, } @inproceedings{11816, abstract = {{In this paper, we consider the Maximum Likelihood (ML) estimation of the parameters of a GAUSSIAN in the presence of censored, i.e., clipped data. We show that the resulting Expectation Maximization (EM) algorithm delivers virtually biasfree and efficient estimates, and we discuss its convergence properties. We also discuss optimal classification in the presence of censored data. Censored data are frequently encountered in wireless LAN positioning systems based on the fingerprinting method employing signal strength measurements, due to the limited sensitivity of the portable devices. Experiments both on simulated and real-world data demonstrate the effectiveness of the proposed algorithms.}}, author = {{Hoang, Manh Kha and Haeb-Umbach, Reinhold}}, booktitle = {{38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, keywords = {{Gaussian processes, Global Positioning System, convergence, expectation-maximisation algorithm, fingerprint identification, indoor radio, signal classification, wireless LAN, EM algorithm, ML estimation, WiFi indoor positioning, censored Gaussian data classification, clipped data, convergence properties, expectation maximization algorithm, fingerprinting method, maximum likelihood estimation, optimal classification, parameters estimation, portable devices sensitivity, signal strength measurements, wireless LAN positioning systems, Convergence, IEEE 802.11 Standards, Maximum likelihood estimation, Parameter estimation, Position measurement, Training, Indoor positioning, censored data, expectation maximization, signal strength, wireless LAN}}, pages = {{3721--3725}}, title = {{{Parameter estimation and classification of censored Gaussian data with application to WiFi indoor positioning}}}, doi = {{10.1109/ICASSP.2013.6638353}}, year = {{2013}}, } @inproceedings{11841, abstract = {{Recently, substantial progress has been made in the field of reverberant speech signal processing, including both single- and multichannel de-reverberation techniques, and automatic speech recognition (ASR) techniques robust to reverberation. To evaluate state-of-the-art algorithms and obtain new insights regarding potential future research directions, we propose a common evaluation framework including datasets, tasks, and evaluation metrics for both speech enhancement and ASR techniques. The proposed framework will be used as a common basis for the REVERB (REverberant Voice Enhancement and Recognition Benchmark) challenge. This paper describes the rationale behind the challenge, and provides a detailed description of the evaluation framework and benchmark results.}}, author = {{Kinoshita, Keisuke and Delcroix, Marc and Yoshioka, Takuya and Nakatani, Tomohiro and Habets, Emanuel and Haeb-Umbach, Reinhold and Leutnant, Volker and Sehr, Armin and Kellermann, Walter and Maas, Roland and Gannot, Sharon and Raj, Bhiksha}}, booktitle = {{ IEEE Workshop on Applications of Signal Processing to Audio and Acoustics }}, keywords = {{Reverberant speech, dereverberation, ASR, evaluation, challenge}}, pages = {{ 22--23 }}, title = {{{The reverb challenge: a common evaluation framework for dereverberation and recognition of reverberant speech}}}, year = {{2013}}, } @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{11909, abstract = {{We present a novel method to exploit correlations of adjacent time-frequency (TF)-slots for a sparseness-based blind speech separation (BSS) system. Usually, these correlations are exploited by some heuristic smoothing techniques in the post-processing of the estimated soft TF masks. We propose a different approach: Based on our previous work with one-dimensional (1D)-hidden Markov models (HMMs) along the time axis we extend the modeling to two-dimensional (2D)-HMMs to exploit both temporal and spectral correlations in the speech signal. Based on the principles of turbo decoding we solved the complex inference of 2D-HMMs by a modified forward-backward algorithm which operates alternatingly along the time and the frequency axis. Extrinsic information is exchanged between these steps such that increasingly better soft time-frequency masks are obtained, leading to improved speech separation performance in highly reverberant recording conditions.}}, author = {{Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}}, booktitle = {{21th European Signal Processing Conference (EUSIPCO 2013)}}, title = {{{Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs}}}, year = {{2013}}, } @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}}, } @inproceedings{11921, abstract = {{In this paper we consider the unsupervised word discovery from phonetic input. We employ a word segmentation algorithm which simultaneously develops a lexicon, i.e., the transcription of a word in terms of a phone sequence, learns a n-gram language model describing word and word sequence probabilities, and carries out the segmentation itself. The underlying statistical model is that of a Pitman-Yor process, a concept known from Bayesian non-parametrics, which allows for an a priori unknown and unlimited number of different words. Using a hierarchy of Pitman-Yor processes, language models of different order can be employed and nesting it with another hierarchy of Pitman-Yor processes on the phone level allows for backing off unknown word unigrams by phone m-grams. We present results on a large-vocabulary task, assuming an error-free phone sequence is given. We finish by discussing options how to cope with noisy phone sequences.}}, author = {{Walter, Oliver and Haeb-Umbach, Reinhold and Chaudhuri, Sourish and Raj, Bhiksha}}, booktitle = {{IEEE International Conference on Robotics and Automation (ICRA 2013)}}, title = {{{Unsupervised Word Discovery from Phonetic Input Using Nested Pitman-Yor Language Modeling}}}, year = {{2013}}, } @inproceedings{11924, author = {{Walter, Oliver and Korthals, Timo and Haeb-Umbach, Reinhold and Raj, Bhiksha}}, booktitle = {{Automatic Speech Recognition and Understanding Workshop (ASRU 2013)}}, title = {{{Hierarchical System for Word Discovery Exploiting DTW-Based Initialization}}}, year = {{2013}}, } @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{11976, author = {{Bloessl, Bastian and Segata, Michele and Sommer, Christoph and Dressler, Falko}}, booktitle = {{Proceedings of the 19th annual international conference on Mobile computing & networking - MobiCom '13}}, isbn = {{9781450319997}}, title = {{{Decoding IEEE 802.11a/g/p OFDM in software using GNU radio}}}, doi = {{10.1145/2500423.2505300}}, year = {{2013}}, } @inproceedings{11977, author = {{Bloessl, Bastian and Segata, Michele and Sommer, Christoph and Dressler, Falko}}, booktitle = {{Proceedings of the second workshop on Software radio implementation forum - SRIF '13}}, isbn = {{9781450321815}}, title = {{{An IEEE 802.11a/g/p OFDM receiver for GNU radio}}}, doi = {{10.1145/2491246.2491248}}, year = {{2013}}, } @inproceedings{12022, author = {{Joerer, Stefan and Segata, Michele and Bloessl, Bastian and Cigno, Renato Lo and Sommer, Christoph and Dressler, Falko}}, booktitle = {{2012 IEEE Vehicular Networking Conference (VNC)}}, isbn = {{9781467349963}}, title = {{{To crash or not to crash: Estimating its likelihood and potentials of beacon-based IVC systems}}}, doi = {{10.1109/vnc.2012.6407441}}, year = {{2013}}, } @article{12025, author = {{Joerer, Stefan and Segata, Michele and Bloessl, Bastian and Lo Cigno, Renato and Sommer, Christoph and Dressler, Falko}}, issn = {{0018-9545}}, journal = {{IEEE Transactions on Vehicular Technology}}, pages = {{1802--1812}}, title = {{{A Vehicular Networking Perspective on Estimating Vehicle Collision Probability at Intersections}}}, doi = {{10.1109/tvt.2013.2287343}}, year = {{2013}}, } @inproceedings{12028, author = {{Klingler, Florian and Dressler, Falko and Cao, Jiannong and Sommer, Christoph}}, booktitle = {{2013 10th Annual Conference on Wireless On-demand Network Systems and Services (WONS)}}, isbn = {{9781479907496}}, title = {{{Use both lanes: Multi-channel beaconing for message dissemination in vehicular networks}}}, doi = {{10.1109/wons.2013.6578342}}, year = {{2013}}, } @inproceedings{12044, author = {{Schwartz, Ramon S. and Ohazulike, Anthony E. and Sommer, Christoph and Scholten, Hans and Dressler, Falko and Havinga, Paul}}, booktitle = {{2012 IEEE Vehicular Networking Conference (VNC)}}, isbn = {{9781467349963}}, title = {{{Fair and adaptive data dissemination for Traffic Information Systems}}}, doi = {{10.1109/vnc.2012.6407432}}, year = {{2013}}, } @article{12045, author = {{Schwartz, Ramon S. and Ohazulike, Anthony E. and Sommer, Christoph and Scholten, Hans and Dressler, Falko and Havinga, Paul}}, issn = {{1570-8705}}, journal = {{Ad Hoc Networks}}, pages = {{428--443}}, title = {{{On the applicability of fair and adaptive data dissemination in traffic information systems}}}, doi = {{10.1016/j.adhoc.2013.09.004}}, year = {{2013}}, } @inproceedings{12064, author = {{Sommer, Christoph and Joerer, Stefan and Dressler, Falko}}, booktitle = {{2012 IEEE Vehicular Networking Conference (VNC)}}, isbn = {{9781467349963}}, title = {{{On the applicability of Two-Ray path loss models for vehicular network simulation}}}, doi = {{10.1109/vnc.2012.6407446}}, year = {{2013}}, } @inproceedings{12065, author = {{Sommer, Christoph and Joerer, Stefan and Segata, Michele and Tonguz, Ozan and Cigno, Renato Lo and Dressler, Falko}}, booktitle = {{2013 Proceedings IEEE INFOCOM}}, isbn = {{9781467359467}}, title = {{{How shadowing hurts vehicular communications and how dynamic beaconing can help}}}, doi = {{10.1109/infcom.2013.6566745}}, year = {{2013}}, } @article{12066, author = {{Sommer, Christoph and Eckhoff, David and Dressler, Falko}}, issn = {{1536-1233}}, journal = {{IEEE Transactions on Mobile Computing}}, pages = {{1733--1745}}, title = {{{IVC in Cities: Signal Attenuation by Buildings and How Parked Cars Can Improve the Situation}}}, doi = {{10.1109/tmc.2013.80}}, year = {{2013}}, } @inproceedings{12979, author = {{Hellebrand, Sybille}}, booktitle = {{14th IEEE Latin American Test Workshop - (LATW'13)}}, publisher = {{IEEE}}, title = {{{Analyzing and Quantifying Fault Tolerance Properties}}}, doi = {{10.1109/latw.2013.6562662}}, year = {{2013}}, }