Search

Being able to estimate speech intelligibility without the need for listening tests would confer great benefits for a wide range of speech processing applications. Many attempts have therefore been made to introduce an objective, and ideally referencefree measure for this purpose. Most works analyze speech intelligibility prediction (SIP) methods from a macroscopic point of view, averaging over longer time spans. This paper, in contrast, presents a theoretical framework for the microscopic evaluation of SIP methods. Within our framework, a Statistically estimated Accuracy based on Theory (StAT) is derived, which numerically quantifies the statistical limitations inherent in microscopic SIP. A state-of-the-art approach to microscopic SIP, namely, the use of automatic speech recognition (ASR) to directly predict listening test results, is evaluated within this framework. The practical results are in good agreement with the theory. As the final contribution, a fully blind DIscriminative Speech intelligibility Predictor (DISP) is introduced and is also evaluated within the StAT framework. It is shown that this novel, blind estimator can predict intelligibility as well as—and often even with better accuracy than—the non-blind ASR-based approach, and that its results are again in good agreement with its theoretically derived performance potential.

In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted attacks can modify an audio input signal in such a way that humans still recognise the same words, while ASR systems are steered to predict a different transcription. In this paper, we propose a defense mechanism against targeted adversarial attacks consisting in removing fast-changing features from the audio signals, either by applying slow feature analysis, a low-pass filter, or both, before feeding the input to the ASR system. We perform an empirical analysis of hybrid ASR models trained on data pre-processed in such a way. While the resulting models perform quite well on benign data, they are significantly more robust against targeted adversarial attacks: Our final, proposed model shows a performance on clean data similar to the baseline model, while being more than four times more robust.

Audio-visual speech recognition (AVSR) can effectively and significantly improve the recognition rates of small-vocabulary systems, compared to their audio-only counterparts. For large-vocabulary systems, however, there are still many difficulties, such as unsatisfactory video recognition accuracies, that make it hard to improve over audio-only baselines. In this paper, we specifically consider such scenarios, focusing on the large-vocabulary task of the LRS2 database, where audio-only performance is far superior to video-only accuracies, making this an interesting and challenging setup for multi-modal integration. To address the inherent difficulties, we propose a new fusion strategy: a recurrent integration network is trained to fuse the state posteriors of multiple single-modality models, guided by a set of model-based and signal-based stream reliability measures. During decoding, this network is used for stream integration within a hybrid recognizer, where it can thus cope with the time-variant reliability and information content of its multiple feature inputs. We compare the results with end-to-end AVSR systems as well as with competitive hybrid baseline models, finding that the new fusion strategy shows superior results, on average even outperforming oracle dynamic stream weighting, which has so far marked the -- realistically unachievable -- upper bound for standard stream weighting. Even though the pure lipreading performance is low, audio-visual integration is helpful under all -- clean, noisy, and reverberant -- conditions. On average, the new system achieves a relative word error rate reduction of 42.18\% compared to the audio-only model, pointing at a high effectiveness of the proposed integration approach.

Identification and localization of sounds are both integral parts of computational auditory scene analysis. Although each can be solved separately, the goal of forming coherent auditory objects and achieving a comprehensive spatial scene understanding suggests pursuing a joint solution of the two problems. This work presents an approach that robustly binds localization with the detection of sound events in a binaural robotic system. Both tasks are joined through the use of spatial stream segregation which produces probabilistic time-frequency masks for individual sources attributable to separate locations, enabling segregated sound event detection operating on these streams. We use simulations of a comprehensive suite of test scenes with multiple co-occurring sound sources, and propose performance measures for systematic investigation of the impact of scene complexity on this segregated detection of sound types. Analyzing the effect of spatial scene arrangement, we show how a robot could facilitate high performance through optimal head rotation. Furthermore, we investigate the performance of segregated detection given possible localization error as well as error in the estimation of number of active sources. Our analysis demonstrates that the proposed approach is an effective method to obtain joint sound event location and type information under a wide range of conditions., Accepted for publication in IEEE/ACM Transactions on Audio, Speech, and Language Processing

Estimating the positions of multiple speakers can be helpful for tasks like automatic speech recognition or speaker diarization. Both applications benefit from a known speaker position when, for instance, applying beamforming or assigning unique speaker identities. Recently, several approaches utilizing acoustic signals augmented with visual data have been proposed for this task. However, both the acoustic and the visual modality may be corrupted in specific spatial regions, for instance due to poor lighting conditions or to the presence of background noise. This paper proposes a novel audiovisual data fusion framework for speaker localization by assigning individual dynamic stream weights to specific regions in the localization space. This fusion is achieved via a neural network, which combines the predictions of individual audio and video trackers based on their time- and location-dependent reliability. A performance evaluation using audiovisual recordings yields promising results, with the proposed fusion approach outperforming all baseline models., 4 pages, 6 figures, ICASSP 2021

End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides very good performance in many tasks. However, under noisy and distorted conditions, the performance still degrades notably. While audio-visual speech recognition can significantly improve the recognition rate of end-to-end models in such poor conditions, it is not obvious how to best utilize any available information on acoustic and visual signal quality and reliability in these models. We thus consider the question of how to optimally inform the transformer/CTC model of any time-variant reliability of the acoustic and visual information streams. We propose a new fusion strategy, incorporating reliability information in a decision fusion net that considers the temporal effects of the attention mechanism. This approach yields significant improvements compared to a state-of-the-art baseline model on the Lip Reading Sentences 2 and 3 (LRS2 and LRS3) corpus. On average, the new system achieves a relative word error rate reduction of 43% compared to the audio-only setup and 31% compared to the audiovisual end-to-end baseline., 5 pages

For many small- and medium-vocabulary tasks, audio-visual speech recognition can significantly improve the recognition rates compared to audio-only systems. However, there is still an ongoing debate regarding the best combination strategy for multi-modal information, which should allow for the translation of these gains to large-vocabulary recognition. While an integration at the level of state-posterior probabilities, using dynamic stream weighting, is almost universally helpful for small-vocabulary systems, in large-vocabulary speech recognition, the recognition accuracy remains difficult to improve. In the following, we specifically consider the large-vocabulary task of the LRS2 database, and we investigate a broad range of integration strategies, comparing early integration and end-to-end learning with many versions of hybrid recognition and dynamic stream weighting. One aspect, which is shown to provide much benefit here, is the use of dynamic stream reliability indicators, which allow for hybrid architectures to strongly profit from the inclusion of visual information whenever the audio channel is distorted even slightly., 5 pages

Sound event localization frameworks based on deep neural networks have shown increased robustness with respect to reverberation and noise in comparison to classical parametric approaches. In particular, recurrent architectures that incorporate temporal context into the estimation process seem to be well-suited for this task. This paper proposes a novel approach to sound event localization by utilizing an attention-based sequence-to-sequence model. These types of models have been successfully applied to problems in natural language processing and automatic speech recognition. In this work, a multi-channel audio signal is encoded to a latent representation, which is subsequently decoded to a sequence of estimated directions-of-arrival. Herein, attentions allow for capturing temporal dependencies in the audio signal by focusing on specific frames that are relevant for estimating the activity and direction-of-arrival of sound events at the current time-step. The framework is evaluated on three publicly available datasets for sound event localization. It yields superior localization performance compared to state-of-the-art methods in both anechoic and reverberant conditions., Comment: Published in Proceedings of the 28th European Signal Processing Conference (EUSIPCO), 2020

Adversarial examples seem to be inevitable. These specifically crafted inputs allow attackers to arbitrarily manipulate machine learning systems. Even worse, they often seem harmless to human observers. In our digital society, this poses a significant threat. For example, Automatic Speech Recognition (ASR) systems, which serve as hands-free interfaces to many kinds of systems, can be attacked with inputs incomprehensible for human listeners. The research community has unsuccessfully tried several approaches to tackle this problem. In this paper we propose a different perspective: We accept the presence of adversarial examples against ASR systems, but we require them to be perceivable by human listeners. By applying the principles of psychoacoustics, we can remove semantically irrelevant information from the ASR input and train a model that resembles human perception more closely. We implement our idea in a tool named DOMPTEUR and demonstrate that our augmented system, in contrast to an unmodified baseline, successfully focuses on perceptible ranges of the input signal. This change forces adversarial examples into the audible range, while using minimal computational overhead and preserving benign performance. To evaluate our approach, we construct an adaptive attacker that actively tries to avoid our augmentations and demonstrate that adversarial examples from this attacker remain clearly perceivable. Finally, we substantiate our claims by performing a hearing test with crowd-sourced human listeners., Comment: Accepted at USENIX Security Symposium 2021

We are addressing two fundamental problems in authorship verification (AV): Topic variability and miscalibration. Variations in the topic of two disputed texts are a major cause of error for most AV systems. In addition, it is observed that the underlying probability estimates produced by deep learning AV mechanisms oftentimes do not match the actual case counts in the respective training data. As such, probability estimates are poorly calibrated. We are expanding our framework from PAN 2020 to include Bayes factor scoring (BFS) and an uncertainty adaptation layer (UAL) to address both problems. Experiments with the 2020/21 PAN AV shared task data show that the proposed method significantly reduces sensitivities to topical variations and significantly improves the system’s calibration.

Sound event localization aims at estimating the positions of sound sources in the environment with respect to an acoustic receiver (e.g. a microphone array). Recent advances in this domain most prominently focused on utilizing deep recurrent neural networks. Inspired by the success of transformer architectures as a suitable alternative to classical recurrent neural networks, this paper introduces a novel transformer-based sound event localization framework, where temporal dependencies in the received multi-channel audio signals are captured via self-attention mechanisms. Additionally, the estimated sound event positions are represented as multivariate Gaussian variables, yielding an additional notion of uncertainty, which many previously proposed deep learning-based systems designed for this application do not provide. The framework is evaluated on three publicly available multi-source sound event localization datasets and compared against state-of-the-art methods in terms of localization error and event detection accuracy. It outperforms all competing systems on all datasets with statistical significant differences in performance., Comment: Accepted at INTERSPEECH 2021

Automatic speech recognition (ASR) systems can be fooled via targeted adversarial examples, which induce the ASR to produce arbitrary transcriptions in response to altered audio signals. However, state-of-the-art adversarial examples typically have to be fed into the ASR system directly, and are not successful when played in a room. Previously published over-the-air adversarial examples fall into one of three categories: they are either handcrafted examples, they are so conspicuous that human listeners can easily recognize the target transcription once they are alerted to its content, or they require precise information about the room where the attack takes place, and are hence not transferable to other rooms. In this paper, we demonstrate the first algorithm that produces generic adversarial examples against hybrid ASR systems, which remain robust in an over-the-air attack that is not adapted to the specific environment. Hence, no prior knowledge of the room characteristics is required. Instead, we use room impulse responses (RIRs) to compute robust adversarial examples for arbitrary room characteristics and employ the ASR system Kaldi to demonstrate the attack. Further, our algorithm can utilize psychoacoustic methods to hide changes of the original audio signal below the human thresholds of hearing. In practical experiments, we show that the adversarial examples work for varying room setups, and that no direct line-of-sight between speaker and microphone is necessary. As a result, an attacker can create inconspicuous adversarial examples for any target transcription and apply these to arbitrary room setups without any prior knowledge.

Traditional computational authorship attribution describes a classification task in a closed-set scenario. Given a finite set of candidate authors and corresponding labeled texts, the objective is to determine which of the authors has written another set of anonymous or disputed texts. In this work, we propose a probabilistic autoencoding framework to deal with this supervised classification task. More precisely, we are extending a variational autoencoder (VAE) with embedded Gaussian mixture model to a Student-$t$ mixture model. Autoencoders have had tremendous success in learning latent representations. However, existing VAEs are currently still bound by limitations imposed by the assumed Gaussianity of the underlying probability distributions in the latent space. In this work, we are extending the Gaussian model for the VAE to a Student-$t$ model, which allows for an independent control of the "heaviness" of the respective tails of the implied probability densities. Experiments over an Amazon review dataset indicate superior performance of the proposed method., Preprint

Tracking and predicting the performance of athletes is of great interest, not only in training science but also, increasingly, for serious hobbyists. The increasing availability and use of smart watches and fitness trackers means that abundant data is becoming available, and the interest to optimally use this data for performance tracking and training optimization is great. One competitive model in this domain is the 3-time-constant fitness-fatigue model by Busso based on the model by Banister and colleagues. In the following, we will show that this model can be written equivalently as a linear, time-variant state-space model. With this understanding, it becomes clear that all methods for optimum tracking in statespace models are also directly applicable here. As an example, we show how a Kalman filter can be combined with the fitness-fatigue model in a mathematically consistent fashion. This gives us the opportunity to optimally consider measurements of performance to adapt the fitness and fatigue estimates in a datadriven manner. Results show that this approach is capable of clearly improving performance tracking and prediction over a range of different scenarios.

Machine learning systems and also, specifically, automatic speech recognition (ASR) systems are vulnerable against adversarial attacks, where an attacker maliciously changes the input. In the case of ASR systems, the most interesting cases are targeted attacks, in which an attacker aims to force the system into recognizing given target transcriptions in an arbitrary audio sample. The increasing number of sophisticated, quasi imperceptible attacks raises the question of countermeasures. In this paper, we focus on hybrid ASR systems and compare four acoustic models regarding their ability to indicate uncertainty under attack: a feed-forward neural network and three neural networks specifically designed for uncertainty quantification, namely a Bayesian neural network, Monte Carlo dropout, and a deep ensemble. We employ uncertainty measures of the acoustic model to construct a simple one-class classification model for assessing whether inputs are benign or adversarial. Based on this approach, we are able to detect adversarial examples with an area under the receiving operator curve score of more than 0.99. The neural networks for uncertainty quantification simultaneously diminish the vulnerability to the attack, which is reflected in a lower recognition accuracy of the malicious target text in comparison to a standard hybrid ASR system.

Authorship verification is the task of analyzing the linguistic patterns of two or more texts to determine whether they were written by the same author or not. The analysis is traditionally performed by experts who consider linguistic features, which include spelling mistakes, grammatical inconsistencies, and stylistics for example. Machine learning algorithms, on the other hand, can be trained to accomplish the same, but have traditionally relied on so-called stylometric features. The disadvantage of such features is that their reliability is greatly diminished for short and topically varied social media texts. In this interdisciplinary work, we propose a substantial extension of a recently published hierarchical Siamese neural network approach, with which it is feasible to learn neural features and to visualize the decision-making process. For this purpose, a new large-scale corpus of short Amazon reviews for text comparison research is compiled and we show that the Siamese network topologies outperform state-of-the-art approaches that were built up on stylometric features. Our linguistic analysis of the internal attention weights of the network shows that the proposed method is indeed able to latch on to some traditional linguistic categories., Accepted for 2019 IEEE International Conference on Big Data (IEEE Big Data 2019)

Authorship verification tries to answer the question if two documents with unknown authors were written by the same author or not. A range of successful technical approaches has been proposed for this task, many of which are based on traditional linguistic features such as n-grams. These algorithms achieve good results for certain types of written documents like books and novels. Forensic authorship verification for social media, however, is a much more challenging task since messages tend to be relatively short, with a large variety of different genres and topics. At this point, traditional methods based on features like n-grams have had limited success. In this work, we propose a new neural network topology for similarity learning that significantly improves the performance on the author verification task with such challenging data sets., Comment: 5 pages, 3 figures, 1 table, presented on ICASSP 2019 in Brighton, UK

Data fusion plays an important role in many technical applications that require efficient processing of multimodal sensory observations. A prominent example is audiovisual signal processing, which has gained increasing attention in automatic speech recognition, speaker localization and related tasks. If appropriately combined with acoustic information, additional visual cues can help to improve the performance in these applications, especially under adverse acoustic conditions. A dynamic weighting of acoustic and visual streams based on instantaneous sensor reliability measures is an efficient approach to data fusion in this context. This article presents a framework that extends the well-established theory of nonlinear dynamical systems with the notion of dynamic stream weights for an arbitrary number of sensory observations. It comprises a recursive state estimator based on the Gaussian filtering paradigm, which incorporates dynamic stream weights into a framework closely related to the extended Kalman filter. Additionally, a convex optimization approach to estimate oracle dynamic stream weights in fully observed dynamical systems utilizing a Dirichlet prior is presented. This serves as a basis for a generic parameter learning framework of dynamic stream weight estimators. The proposed system is application-independent and can be easily adapted to specific tasks and requirements. A study using audiovisual speaker tracking tasks is considered as an exemplary application in this work. An improved tracking performance of the dynamic stream-weight-based estimation framework over state-of-the-art methods is demonstrated in the experiments.

Voice interfaces are becoming accepted widely as input methods for a diverse set of devices. This development is driven by rapid improvements in automatic speech recognition (ASR), which now performs on par with human listening in many tasks. These improvements base on an ongoing evolution of DNNs as the computational core of ASR. However, recent research results show that DNNs are vulnerable to adversarial perturbations, which allow attackers to force the transcription into a malicious output. In this paper, we introduce a new type of adversarial examples based on psychoacoustic hiding. Our attack exploits the characteristics of DNN-based ASR systems, where we extend the original analysis procedure by an additional backpropagation step. We use this backpropagation to learn the degrees of freedom for the adversarial perturbation of the input signal, i.e., we apply a psychoacoustic model and manipulate the acoustic signal below the thresholds of human perception. To further minimize the perceptibility of the perturbations, we use forced alignment to find the best fitting temporal alignment between the original audio sample and the malicious target transcription. These extensions allow us to embed an arbitrary audio input with a malicious voice command that is then transcribed by the ASR system, with the audio signal remaining barely distinguishable from the original signal. In an experimental evaluation, we attack the state-of-the-art speech recognition system Kaldi and determine the best performing parameter and analysis setup for different types of input. Our results show that we are successful in up to 98% of cases with a computational effort of fewer than two minutes for a ten-second audio file. Based on user studies, we found that none of our target transcriptions were audible to human listeners, who still understand the original speech content with unchanged accuracy.

Humans use a variety of approaches to reference objects in the external world, including verbal descriptions, hand and head gestures, eye gaze or any combination of them. The amount of useful information from each modality, however, may vary depending on the specific person and on several other factors. For this reason, it is important to learn the correct combination of inputs for inferring the best-fitting reference. In this paper, we investigate appropriate speaker-dependent and independent fusion strategies in a multimodal reference resolution task. We show that without any change in the modality models, only through an optimized fusion technique, it is possible to reduce the error rate of the system on a reference resolution task by more than 50%.

Linear discriminant analysis (LDA) is a powerful technique in pattern recognition to reduce the dimensionality of data vectors. It maximizes discriminability by retaining only those directions that minimize the ratio of within-class and between-class variance. In this paper, using the same principles as for conventional LDA, we propose to employ uncertainties of the noisy or distorted input data in order to estimate maximally discriminant directions. We demonstrate the efficiency of the proposed uncertain LDA on two applications using state-of-the-art techniques. First, we experiment with an automatic speech recognition task, in which the uncertainty of observations is imposed by real-world additive noise. Next, we examine a full-scale speaker recognition system, considering the utterance duration as the source of uncertainty in authenticating a speaker. The experimental results show that when employing an appropriate uncertainty estimation algorithm, uncertain LDA outperforms its conventional LDA counterpart.

Audio-visual speech recognition is a promising approach to tackling the problem of reduced recognition rates under adverse acoustic conditions. However, finding an optimal mechanism for combining multi-modal information remains a challenging task. Various methods are applicable for integrating acoustic and visual information in Gaussian-mixture-model-based speech recognition, e.g., via dynamic stream weighting. The recent advances of deep neural network (DNN)-based speech recognition promise improved performance when using audio-visual information. However, the question of how to optimally integrate acoustic and visual information remains. In this paper, we propose a state-based integration scheme that uses dynamic stream weights in DNN-based audio-visual speech recognition. The dynamic weights are obtained from a time-variant reliability estimate that is derived from the audio signal. We show that this state-based integration is superior to early integration of multi-modal features, even if early integration also includes the proposed reliability estimate. Furthermore, the proposed adaptive mechanism is able to outperform a fixed weighting approach that exploits oracle knowledge of the true signal-to-noise ratio.

Automatic speech recognition (ASR) performance suffers severely from non-stationary noise, precluding widespread use of ASR in natural environments. Recently, so-termed uncertainty-of-observation techniques have helped to recover good performance. These consider the clean speech features as a hidden variable, of which the observable features are only an imperfect estimate. An estimated error variance of features is therefore used to further guide recognition. Based on the same idea, we introduce a new strategy: Reducing the speech feature dimensionality for optimal discriminance under observation uncertainty can yield significantly improved recognition performance, and is derived easily via Fisher's criterion of discriminant analysis.

This paper presents a new approach for increasing the robustness of multi-channel automatic speech recognition in noisy and reverberant multi-source environments. The proposed method uses uncertainty propagation techniques to dynamically compensate the speech features and the acoustic models for the observation uncertainty determined at the beamforming stage. We present and analyze two methods that allow integrating classical multi-channel signal processing approaches like delay and sum beamformers or Zelinski-type Wiener filters, with uncertainty-of-observation techniques like uncertainty decoding or modified imputation. An analysis of the results on the PASCAL-CHiME task shows that this approach consistently outperforms conventional beamformers with a minimal increase in computational complexity. The use of dynamic compensation based on observation uncertainty also outperforms conventional static adaptation with no need of adaptation data.

Automatic speech recognition (ASR) has become a widespread and convenient mode of human-machine interaction, but it is still not sufficiently reliable when used under highly noisy or reverberant conditions. One option for achieving far greater robustness is to include another modality that is unaffected by acoustic noise, such as video information. Currently the most successful approaches for such audiovisual ASR systems, coupled hidden Markov models (HMMs) and turbo decoding, both allow for slight asynchrony between audio and video features, and significantly improve recognition rates in this way. However, both typically still neglect residual errors in the estimation of audio features, so-called observation uncertainties. This paper compares two strategies for adding these observation uncertainties into the decoder, and shows that significant recognition rate improvements are achievable for both coupled HMMs and turbo decoding.

In medicine and other high-tech sectors, mobile RFID or sensor transponder systems are designed with high-Q antenna coils to increase the energy efficiency. Hence, the range of inductively coupled systems is improved; however, the bandwidth is decreased by 1 over Q . As a result, the reading performance is not limited by the energy supply, but instead by a high bit error rate. In this paper, we describe how the data detection in such narrow-band systems can be improved by a multilevel decoding scheme composed of an advanced maximum-likelihood receiver in the first stage and a soft Viterbi decoding scheme utilizing time variant reliability information in the second stage. An analysis of potential time-variant reliability information is given. The analysis relies on an underlying Bayesian model, which provides an a-posteriori probability indicating the reliability of the received input. As the final building block, a last decoding stage is discussed, which can be composed of a forward error correction that further exploits the reliability information at the second decoder output. Overall, the suggested system architecture results in a notable improvement of both bit and packet error rate, thus allowing the use of high-quality-factor antennas for efficient and reliable mobile RFID systems.

International audience; In order to improve the ASR performance in noisy environments , distorted speech is typically pre-processed by a speech enhancement algorithm, which usually results in a speech estimate containing residual noise and distortion. We may also have some measures of uncertainty or variance of the estimate. Uncertainty decoding is a framework that utilizes this knowledge of uncertainty in the input features during acoustic model scoring. Such frameworks have been well explored for traditional probabilistic models, but their optimal use for deep neural network (DNN)-based ASR systems is not yet clear. In this paper, we study the propagation of observation uncertainties through the layers of a DNN-based acoustic model. Since this is intractable due to the nonlinearities of the DNN, we employ approximate propagation methods, including Monte Carlo sampling , the unscented transform, and the piecewise exponential approximation of the activation function, to estimate the distribution of acoustic scores. Finally, the expected value of the acoustic score distribution is used for decoding, which is shown to further improve the ASR accuracy on the CHiME database, relative to a highly optimized DNN baseline.

Estimation of the direction of arrival (DoA) of speakers in reverberant environments is an important audio signal processing task in a wide range of applications. Recently, a reverberation-robust method for DoA estimation has been developed. It is based on the identification of time-frequency bins that are dominated by the direct path from the source. As the DoA statistics was found to have a multimodal distribution, clustering using Gaussian mixture modeling improved localization accuracy. However, this method employed linear statistics over the azimuth and elevation angles, therefore introducing between 0 and 360 degrees azimuth. This work explores the use of spherical statistics in the direct-path dominance approach to speaker localization in reverberant rooms, providing a more suitable angular representation. Theoretical and experimental aspects of the proposed approach are investigated and validated using a computer simulation of a speaker in a room.

Hearing models for tasks like auditory scene analysis or sound-quality judgments can run into severe problems when acting in a purely bottom-up, that is, signal driven manner, as they may have to follow up on all possible output options until a final decision has been taken. This may lead to a combinatorial explosion. A way out is the inclusion of top-down, that is, hypothesis-driven processes. In top-down processing, the number of states to be evaluated can be reduced substantially, when the system knows what to look for and thereby focuses attention on states which make sense in a given specific situation. To implement adequate top-down processes, various feedback loops will be included in current models, some more specific, others more general. The general ones originate from the concept that the listener model ("artificial listener") actively explores acoustic scenes and thereby develops its aural world in an autonomous way. Following this notion, it is attempted to model listeners according to the autonomous-agents paradigm, where agents actively learn and listen.

When a number of speakers are simultaneously active, for example in meetings or noisy public places, the sources of interest need to be separated from interfering speakers and from each other in order to be robustly recognized. Independent component analysis (ICA) has proven a valuable tool for this purpose. However, ICA outputs can still contain strong residual components of the interfering speakers whenever noise or reverberation is high. In such cases, nonlinear postprocessing can be applied to the ICA outputs, for the purpose of reducing remaining interferences. In order to improve robustness to the artefacts and loss of information caused by this process, recognition can be greatly enhanced by considering the processed speech feature vector as a random variable with time-varying uncertainty, rather than as deterministic. The aim of this paper is to show the potential to improve recognition of multiple overlapping speech signals through nonlinear postprocessing together with uncertainty-based decoding techniques.

The problem of blind source separation (BSS) of convolved acoustic signals is of great interest for many classes of applications. Due to the convolutive mixing process, the source separation is performed in the frequency domain, using independent component analysis (ICA). However, frequency domain BSS involves several major problems that must be solved. One of these is the permutation problem. The permutation ambiguity of ICA needs to be resolved so that each separated signal contains the frequency components of only one source signal. This article presents a class of methods for solving the permutation problem based on information theoretic distance measures. The proposed algorithms have been tested on different real-room speech mixtures with different reverberation times in conjunction with different ICA algorithms.