@techreport{11923, abstract = {{In this paper we show that recently developed algorithms for unsupervised word segmentation can be a valuable tool for the documentation of endangered languages. We applied an unsupervised word segmentation algorithm based on a nested Pitman-Yor language model to two austronesian languages, Wooi and Waima'a. The algorithm was then modified and parameterized to cater the needs of linguists for high precision of lexical discovery: We obtained a lexicon precision of of 69.2\% and 67.5\% for Wooi and Waima'a, respectively, if single-letter words and words found less than three times were discarded. A comparison with an English word segmentation task showed comparable performance, verifying that the assumptions underlying the Pitman-Yor language model, the universality of Zipf's law and the power of n-gram structures, do also hold for languages as exotic as Wooi and Waima'a.}}, author = {{Walter, Oliver and Haeb-Umbach, Reinhold and Strunk, Jan and P. Himmelmann, Nikolaus }}, title = {{{Lexicon Discovery for Language Preservation using Unsupervised Word Segmentation with Pitman-Yor Language Models (FGNT-2015-01)}}}, year = {{2015}}, } @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}}, } @inproceedings{11746, abstract = {{ "A method for nonstationary noise robust automatic speech recognition (ASR) is to first estimate the changing noise statistics and second clean up the features prior to recognition accordingly. Here, the first is accomplished by noise tracking in the spectral domain, while the second relies on Bayesian enhancement in the feature domain. In this way we take advantage of our recently proposed maximum a-posteriori based (MAP-B) noise power spectral density estimation algorithm, which is able to estimate the noise statistics even in time-frequency bins dominated by speech. We show that MAP-B noise tracking leads to an improved noise model estimate in the feature domain compared to estimating noise in speech absence periods only, if the bias resulting from the nonlinear transformation from the spectral to the feature domain is accounted for. Consequently, ASR results are improved, as is shown by experiments conducted on the Aurora IV database." }}, author = {{Chinaev, Aleksej and Puels, Marc and Haeb-Umbach, Reinhold}}, booktitle = {{11. ITG Fachtagung Sprachkommunikation (ITG 2014)}}, title = {{{Spectral Noise Tracking for Improved Nonstationary Noise Robust ASR}}}, year = {{2014}}, } @inproceedings{11752, abstract = {{ "In this contribution we derive a variational EM (VEM) algorithm for model selection in complex Watson mixture models, which have been recently proposed as a model of the distribution of normalized microphone array signals in the short-time Fourier transform domain. The VEM algorithm is applied to count the number of active sources in a speech mixture by iteratively estimating the mode vectors of the Watson distributions and suppressing the signals from the corresponding directions. A key theoretical contribution is the derivation of the MMSE estimate of a quadratic form involving the mode vector of the Watson distribution. The experimental results demonstrate the effectiveness of the source counting approach at moderately low SNR. It is further shown that the VEM algorithm is more robust w.r.t. used threshold values." }}, author = {{Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}}, booktitle = {{39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)}}, title = {{{Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models}}}, year = {{2014}}, } @inproceedings{11753, abstract = {{This contribution describes a step-wise source counting algorithm to determine the number of speakers in an offline scenario. Each speaker is identified by a variational expectation maximization (VEM) algorithm for complex Watson mixture models and therefore directly yields beamforming vectors for a subsequent speech separation process. An observation selection criterion is proposed which improves the robustness of the source counting in noise. The algorithm is compared to an alternative VEM approach with Gaussian mixture models based on directions of arrival and shown to deliver improved source counting accuracy. The article concludes by extending the offline algorithm towards a low-latency online estimation of the number of active sources from the streaming input data.}}, author = {{Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}}, booktitle = {{14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)}}, keywords = {{Accuracy, Acoustics, Estimation, Mathematical model, Soruce separation, Speech, Vectors, Bayes methods, Blind source separation, Directional statistics, Number of speakers, Speaker diarization}}, pages = {{213--217}}, title = {{{Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models}}}, year = {{2014}}, } @inproceedings{11814, abstract = {{ "In this paper we present an algorithm for the unsupervised segmentation of a lattice produced by a phoneme recognizer into words. Using a lattice rather than a single phoneme string accounts for the uncertainty of the recognizer about the true label sequence. An example application is the discovery of lexical units from the output of an error-prone phoneme recognizer in a zero-resource setting, where neither the lexicon nor the language model (LM) is known. We propose a computationally efficient iterative approach, which alternates between the following two steps: First, the most probable string is extracted from the lattice using a phoneme LM learned on the segmentation result of the previous iteration. Second, word segmentation is performed on the extracted string using a word and phoneme LM which is learned alongside the new segmentation. We present results on lattices produced by a phoneme recognizer on the WSJCAM0 dataset. We show that our approach delivers superior segmentation performance than an earlier approach found in the literature, in particular for higher-order language models. " }}, author = {{Heymann, Jahn and Walter, Oliver and Haeb-Umbach, Reinhold and Raj, Bhiksha}}, booktitle = {{39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)}}, title = {{{Iterative Bayesian Word Segmentation for Unspuervised Vocabulary Discovery from Phoneme Lattices}}}, year = {{2014}}, } @inproceedings{11831, abstract = {{ "Several self-localization algorithms have been proposed, that determine the positions of either acoustic or visual sensors autonomously. Usually these positions are given in a modality specific coordinate system, with an unknown rotation, translation and scale between the different systems. For a joint audiovisual tracking, where the different modalities support each other, the two modalities need to be mapped into a common coordinate system. In this paper we propose to estimate this mapping based on audiovisual correlates, i.e., a speaker that can be localized by both, a microphone and a camera network separately. The voice is tracked by a microphone network, which had to be calibrated by a self-localization algorithm at first, and the head is tracked by a calibrated camera network. Unlike existing Singular Value Decomposition based approaches to estimate the coordinate system mapping, we propose to perform an estimation in the shape domain, which turns out to be computationally more efficient. Simulations of the self-localization of an acoustic sensor network and a following coordinate mapping for a joint speaker localization showed a significant improvement of the localization performance, since the modalities were able to support each other." }}, author = {{Jacob, Florian and Haeb-Umbach, Reinhold}}, booktitle = {{11. ITG Fachtagung Sprachkommunikation (ITG 2014)}}, title = {{{Coordinate Mapping Between an Acoustic and Visual Sensor Network in the Shape Domain for a Joint Self-Calibrating Speaker Tracking}}}, year = {{2014}}, } @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{11867, abstract = {{New waves of consumer-centric applications, such as voice search and voice interaction with mobile devices and home entertainment systems, increasingly require automatic speech recognition (ASR) to be robust to the full range of real-world noise and other acoustic distorting conditions. Despite its practical importance, however, the inherent links between and distinctions among the myriad of methods for noise-robust ASR have yet to be carefully studied in order to advance the field further. To this end, it is critical to establish a solid, consistent, and common mathematical foundation for noise-robust ASR, which is lacking at present. This article is intended to fill this gap and to provide a thorough overview of modern noise-robust techniques for ASR developed over the past 30 years. We emphasize methods that are proven to be successful and that are likely to sustain or expand their future applicability. We distill key insights from our comprehensive overview in this field and take a fresh look at a few old problems, which nevertheless are still highly relevant today. Specifically, we have analyzed and categorized a wide range of noise-robust techniques using five different criteria: 1) feature-domain vs. model-domain processing, 2) the use of prior knowledge about the acoustic environment distortion, 3) the use of explicit environment-distortion models, 4) deterministic vs. uncertainty processing, and 5) the use of acoustic models trained jointly with the same feature enhancement or model adaptation process used in the testing stage. With this taxonomy-oriented review, we equip the reader with the insight to choose among techniques and with the awareness of the performance-complexity tradeoffs. The pros and cons of using different noise-robust ASR techniques in practical application scenarios are provided as a guide to interested practitioners. The current challenges and future research directions in this field is also carefully analyzed.}}, author = {{Li, Jinyu and Deng, Li and Gong, Yifan and Haeb-Umbach, Reinhold}}, journal = {{IEEE Transactions on Audio, Speech and Language Processing}}, keywords = {{Speech recognition, compensation, distortion modeling, joint model training, noise, robustness, uncertainty processing}}, number = {{4}}, pages = {{745--777}}, title = {{{An Overview of Noise-Robust Automatic Speech Recognition}}}, doi = {{10.1109/TASLP.2014.2304637}}, volume = {{22}}, year = {{2014}}, } @inproceedings{11918, abstract = {{In this paper, we investigate unsupervised acoustic model training approaches for dysarthric-speech recognition. These models are first, frame-based Gaussian posteriorgrams, obtained from Vector Quantization (VQ), second, so-called Acoustic Unit Descriptors (AUDs), which are hidden Markov models of phone-like units, that are trained in an unsupervised fashion, and, third, posteriorgrams computed on the AUDs. Experiments were carried out on a database collected from a home automation task and containing nine speakers, of which seven are considered to utter dysarthric speech. All unsupervised modeling approaches delivered significantly better recognition rates than a speaker-independent phoneme recognition baseline, showing the suitability of unsupervised acoustic model training for dysarthric speech. While the AUD models led to the most compact representation of an utterance for the subsequent semantic inference stage, posteriorgram-based representations resulted in higher recognition rates, with the Gaussian posteriorgram achieving the highest slot filling F-score of 97.02%. Index Terms: unsupervised learning, acoustic unit descriptors, dysarthric speech, non-negative matrix factorization}}, author = {{Walter, Oliver and Despotovic, Vladimir and Haeb-Umbach, Reinhold and Gemmeke, Jrt and Ons, Bart and Van hamme, Hugo}}, booktitle = {{INTERSPEECH 2014}}, title = {{{An Evaluation of Unsupervised Acoustic Model Training for a Dysarthric Speech Interface}}}, year = {{2014}}, } @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}}, } @inproceedings{11716, abstract = {{The accuracy of automatic speech recognition systems in noisy and reverberant environments can be improved notably by exploiting the uncertainty of the estimated speech features using so-called uncertainty-of-observation techniques. In this paper, we introduce a new Bayesian decision rule that can serve as a mathematical framework from which both known and new uncertainty-of-observation techniques can be either derived or approximated. The new decision rule in its direct form leads to the new significance decoding approach for Gaussian mixture models, which results in better performance compared to standard uncertainty-of-observation techniques in different additive and convolutive noise scenarios.}}, author = {{Abdelaziz, Ahmed H. and Zeiler, Steffen and Kolossa, Dorothea and Leutnant, Volker and Haeb-Umbach, Reinhold}}, booktitle = {{Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on}}, issn = {{1520-6149}}, keywords = {{Bayes methods, Gaussian processes, convolution, decision theory, decoding, noise, reverberation, speech coding, speech recognition, Bayesian decision rule, GMM, Gaussian mixture models, additive noise scenarios, automatic speech recognition systems, convolutive noise scenarios, decoding approach, mathematical framework, reverberant environments, significance decoding, speech feature estimation, uncertainty-of-observation techniques, Hidden Markov models, Maximum likelihood decoding, Noise, Speech, Speech recognition, Uncertainty, Uncertainty-of-observation, modified imputation, noise robust speech recognition, significance decoding, uncertainty decoding}}, pages = {{6827--6831}}, title = {{{GMM-based significance decoding}}}, doi = {{10.1109/ICASSP.2013.6638984}}, year = {{2013}}, } @inproceedings{11740, abstract = {{In this contribution we derive the Maximum A-Posteriori (MAP) estimates of the parameters of a Gaussian Mixture Model (GMM) in the presence of noisy observations. We assume the distortion to be white Gaussian noise of known mean and variance. An approximate conjugate prior of the GMM parameters is derived allowing for a computationally efficient implementation in a sequential estimation framework. Simulations on artificially generated data demonstrate the superiority of the proposed method compared to the Maximum Likelihood technique and to the ordinary MAP approach, whose estimates are corrected by the known statistics of the distortion in a straightforward manner.}}, author = {{Chinaev, Aleksej and Haeb-Umbach, Reinhold}}, booktitle = {{38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, keywords = {{Gaussian noise, maximum likelihood estimation, parameter estimation, GMM parameter, Gaussian mixture model, MAP estimation, Map-based estimation, maximum a-posteriori estimation, maximum likelihood technique, noisy observation, sequential estimation framework, white Gaussian noise, Additive noise, Gaussian mixture model, Maximum likelihood estimation, Noise measurement, Gaussian mixture model, Maximum a posteriori estimation, Maximum likelihood estimation}}, pages = {{3352--3356}}, title = {{{MAP-based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations}}}, doi = {{10.1109/ICASSP.2013.6638279}}, year = {{2013}}, } @inproceedings{11742, abstract = {{In this paper we present an improved version of the recently proposed Maximum A-Posteriori (MAP) based noise power spectral density estimator. An empirical bias compensation and bandwidth adjustment reduce bias and variance of the noise variance estimates. The main advantage of the MAP-based postprocessor is its low estimation variance. The estimator is employed in the second stage of a two-stage single-channel speech enhancement system, where eight different state-of-the-art noise tracking algorithms were tested in the first stage. While the postprocessor hardly affects the results in stationary noise scenarios, it becomes the more effective the more nonstationary the noise is. The proposed postprocessor was able to improve all systems in babble noise w.r.t. the perceptual evaluation of speech quality performance.}}, author = {{Chinaev, Aleksej and Haeb-Umbach, Reinhold and Taghia, Jalal and Martin, Rainer}}, booktitle = {{38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)}}, issn = {{1520-6149}}, pages = {{7477--7481}}, title = {{{Improved Single-Channel Nonstationary Noise Tracking by an Optimized MAP-based Postprocessor}}}, doi = {{10.1109/ICASSP.2013.6639116}}, year = {{2013}}, } @inproceedings{11762, abstract = {{Among the different configurations of multi-microphone systems, e.g., in applications of speech dereverberation or denoising, we consider the case without a priori information of the microphone-array geometry. This naturally invokes explicit or implicit identification of source-receiver transfer functions as an indirect description of the microphone-array configuration. However, this blind channel identification (BCI) has been difficult due to the lack of unique identifiability in the presence of observation noise or near-common channel zeros. In this paper, we study the implicit BCI performance of blind signal enhancement techniques such as the adaptive principal component analysis (PCA) or the iterative blind equalization and channel identification (BENCH). To this end, we make use of a recently proposed metric, the normalized filter-projection misalignment (NFPM), which is tailored for BCI evaluation in ill-conditioned (e.g., noisy) scenarios. The resulting understanding of implicit BCI performance can help to judge the behavior of multi-microphone speech enhancement systems and the suitability of implicit BCI to serve channel-based (i.e., channel-informed) enhancement.}}, author = {{Enzner, Gerald and Schmid, Dominic and Haeb-Umbach, Reinhold}}, booktitle = {{21th European Signal Processing Conference (EUSIPCO 2013)}}, title = {{{On the Acoustic Channel Identification in Multi-Microphone Systems via Adaptive Blind Signal Enhancement Techniques}}}, year = {{2013}}, } @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}}, }