Stefan Goetze

Regularization for Partial Multichannel Equalization for Speech Dereverberation

Acoustic multichannel equalization techniques such as the multiple-input/output inverse theorem (MINT), which aim to equalize the room impulse responses (RIRs) between the source and the microphone array, are known to be highly sensitive to RIR estimation errors. To increase robustness, it has been proposed to incorporate regularization in order to decrease the energy of the equalization filters. In addition, more robust partial multichannel equalization techniques such as relaxed multichannel least-squares (RMCLS) and channel shortening (CS) have recently been proposed. In this paper, we propose a partial multichannel equalization technique based on MINT (P-MINT) which aims to shorten the RIR. Furthermore, we investigate the effectiveness of incorporating regularization to further increase the robustness of P-MINT and the aforementioned partial multichannel equalization techniques, i.e., RMCLS and CS. In addition, we introduce an automatic non-intrusive procedure for determining the regularization parameter based on the L-curve. Simulation results using measured RIRs show that incorporating regularization in P-MINT yields a significant performance improvement in the presence of RIR estimation errors, whereas a smaller performance improvement is observed when incorporating regularization in RMCLS and CS. Furthermore, it is shown that the intrusively regularized P-MINT technique outperforms all other investigated intrusively regularized multichannel equalization techniques in terms of perceptual speech quality (PESQ). Finally, it is shown that the automatic non-intrusive regularization parameter in regularized P-MINT leads to a very similar performance as the intrusively determined optimal regularization parameter, making regularized P-MINT a robust, perceptually advantageous, and practically applicable multichannel equalization technique for speech dereverberation.

The Lower Saxony research network design of environments for ageing: towards interdisciplinary research on information and communication technologies in ageing societies

Worldwide, ageing societies are bringing challenges for independent living and healthcare. Health-enabling technologies for pervasive healthcare and sensor-enhanced health information systems offer new opportunities for care. In order to identify, implement and assess such new information and communication technologies (ICT) the ‘Lower Saxony Research Network Design of Environments for Ageing’ (GAL) has been launched in 2008 as interdisciplinary research project. In this publication, we inform about the goals and structure of GAL, including first outcomes, as well as to discuss the potentials and possible barriers of such highly interdisciplinary research projects in the field of health-enabling technologies for pervasive healthcare. Although GALs high interdisciplinarity at the beginning slowed down the speed of research progress, we can now work on problems, which can hardly be solved by one or few disciplines alone. Interdisciplinary research projects on ICT in ageing societies are needed and recommended.

Acoustic user interfaces for ambient-assisted living technologies

This contribution discusses technologies for acoustic user interaction in ambient-assisted living (AAL) scenarios. Acoustic user interfaces allow for a natural and convenient way to interact with technical systems e.g. via sound or speech presentation or via speech input by means of automatic speech recognition (ASR) as well as by detection and classification of acoustic events. Older persons targeted by AAL technologies especially need more easy-to-use methods to interact with inherently complex supporting technology. As an example we designed and evaluated an application for acoustic user interaction with a multi-media reminder and calendar system. For this purpose, mainly older participants were involved in user studies to continuously evaluate and support the development strictly following a user-centred design process. The results suggest a wide acceptance of acoustic user interfaces by older users either for controlling inherently complex AAL systems by using robust ASR technologies or as a natural and ambient way of presenting information to the user. However, further research is needed to increase the robustness of ASR systems when using hands-free equipment, i.e. to provide a real ambient way of interaction, and to introduce personalised speech and sound presentation schemes accounting for the individual hearing capabilities and sound preferences.

Information and communication technologies for promoting and sustaining quality of life, health and self-sufficiency in ageing societies – outcomes of the Lower Saxony Research Network Design of Environments for Ageing (GAL)

Many societies across the world are confronted with demographic changes, usually related to increased life expectancy and, often, relatively low birth rates. Information and communication technologies (ICT) may contribute to adequately support senior citizens in aging societies with respect to quality of life and quality and efficiency of health care processes. For investigating and for providing answers on whether new information and communication technologies can contribute to keeping, or even improving quality of life, health and self-sufficiency in ageing societies through new ways of living and new forms of care, the Lower Saxony Research Network Design of Environments for Ageing (GAL) had been established as a five years research project, running from 2008 to 2013. Ambient-assisted living (AAL) technologies in personal and home environments were especially important. In this article we report on the GAL project, and present some of its major outcomes after five years of research. We report on major challenges and lessons learned in running and organizing such a large, inter- and multidisciplinary project and discuss GAL in the context of related research projects. With respect to research outcomes, we have, for example, learned new knowledge about multimodal and speech-based human–machine-interaction mechanisms for persons with functional restrictions, and identified new methods and developed new algorithms for identifying activities of daily life and detecting acute events, particularly falls. A total of 79 apartments of senior citizens had been equipped with specific “GAL technology”, providing new insights into the use of sensor data for smart homes. Major challenges we had to face were to deal constructively with GAL’s highly inter- and multidisciplinary aspects, with respect to research into GAL’s application scenarios, shifting from theory and lab experimentation to field tests, and the complexity of organizing and, in our view, successfully managing such a large project. Overall it can be stated that, from our point of view, the GAL research network has been run successfully and has achieved its major research objectives. Since we now know much more on how and where to use AAL technologies for new environments of living and new forms of care, a future focus for research can now be outlined for systematically planned studies, scientifically exploring the benefits of AAL technologies for senior citizens, in particular with respect to quality of life and the quality and efficiency of health care.

Automatic acoustic siren detection in traffic noise by part-based models

State-of-the-art classifiers like hidden Markov models (HMMs) in combination with mel-frequency cepstral coefficients (MFCCs) are flexible in time but rigid in the spectral dimension. In contrast, part-based models (PBMs) originally proposed in computer vision consist of parts in a fully deformable configuration. The present contribution proposes to employ PBMs in the spectro-temporal domain for detection of emergency siren sounds in traffic noise,standard generative training resulting in a classifier that is robust to shifts in frequency induced, e.g., by Doppler-shift effects. Two improvements over standard machine learning techniques for PBM estimation are proposed: (i) Spectro-temporal part (“appearance”) extraction is initialized by interest point detection instead of random initialization and (ii) a discriminative training approach in addition to standard generative training is implemented. Evaluation with self-recorded police sirens and traffic noise gathered on-line demonstrates that PBMs are successful in acoustic siren detection. One hand-labeled and two machine learned PBMs are compared to standard HMMs employing mel-spectrograms and MFCCs in clean and multi condition (multiple SNR) training settings. Results show that in clean condition training, hand-labeled PBMs and HMMs outperform machine-learned PBMs already for test data with moderate additive noise. In multi condition training, the machine learned PBMs outperform HMMs on most SNRs, achieving high accuracies and being nearly optimal up to 5 dB SNR. Thus, our simulation results show that PBMs are a promising approach for acoustic event detection (AED).

Acoustic Monitoring and Localization for Social Care

Increase in the number of older people due to demographic changes poses great challenges to the social healthcare systems both in the Western and as well as in the Eastern countries. Support for older people by formal care givers leads to enormous temporal and personal efforts. Therefore, one of the most important goals is to increase the efficiency and effectiveness of today’s care. This can be achieved by the use of assistive technologies. These technologies are able to increase the safety of patients or to reduce the time needed for tasks that do not relate to direct interaction between the care giver and the patient. Motivated by this goal, this contribution focuses on applications of acoustic technologies to support users and care givers in ambient assisted living (AAL) scenarios. Acoustic sensors are small, unobtrusive and can be added to already existing care or living environments easily. The information gathered by the acoustic sensors can be analyzed to calculate the position of the user by localization and the context by detection and classification of acoustic events in the captured acoustic signal. By doing this, possibly dangerous situations like falls, screams or an increased amount of coughs can be detected and appropriate actions can be initialized by an intelligent autonomous system for the acoustic monitoring of older persons. The proposed system is able to reduce the false alarm rate compared to other existing and commercially available approaches that basically rely only on the acoustic level. This is due to the fact that it explicitly distinguishes between the various acoustic events and provides information on the type of emergency that has taken place. Furthermore, the position of the acoustic event can be determined as contextual information by the system that uses only the acoustic signal. By this, the position of the user is known even if she or he does not wear a localization device such as a radio-frequency identification (RFID) tag. Category: Smart and intelligent computing

Voice activity detection driven acoustic event classification for monitoring in smart homes

This contribution focuses on acoustic event detection and classification for monitoring of elderly people in ambient assistive living environments such as smart homes or nursing homes. We describe an autonomous system for robust detection of acoustic events in various practically relevant acoustic situations that benefits from a voice activity detection inspired preprocessing mechanism. Therefore, various already established voice activity detection schemes have been evaluated beforehand. As a specific use case, we address coughing as an acoustic event of interest which can be interpreted as an indicator for a potentially upcoming illness. After the detection of such events using a psychoacoustically motivated spectro-temporal representation (the so-called cochleogram), we forward its output to a statistical event modeling stage for automatic instantaneous emergency classification and long-term monitoring. The parameters derived by this procedure can then be used to inform medical or care-service personal.

Quality assessment for listening-room compensation algorithms

In this contribution various objective measures that can be used to evaluate speech dereverberation algorithms by means of listening-room compensation (LRC) are compared to subjective listening tests. It is shown that technical measures describing the impulse responses are suitable for evaluation of such algorithms. Most signal-based objective measures fail to judge the specific distortions that may be introduced by LRC algorithms like late reverberation since these artifacts are small in amplitude but perceptually relevant due to the loss of masking of the room impulse response. Only one signal-based measure, the so-called perceptual similarity measure (PSM), showed high correlation with subjective rating for the given test setup.

Objective perceptual quality assessment for self-steering binaural hearing aid microphone arrays

In this study a self-steering beamformer with binaural output for a head-worn microphone array is investigated in simulated and real- world conditions. The influence of the underlying sound propagation model on the estimation accuracy of the direction of arrival (DOA) estimation algorithm and the overall performance of the combined DOA-beamformer-system is evaluated. For this, technical performance measures as well as objective quality measures based on perceptual models of the auditory system are used. The self-steering beamformer showed better performance than a beamformer with fixed look-direction for SNR values above -2 dB if the propagation model includes at least a coarse head model.

A study on speech quality and speech intelligibility measures for quality assessment of single-channel dereverberation algorithms

This paper reports on the evaluation of several objective quality measures for predicting the quality of the dereverberated speech signals. The correlations between subjective quality assessment for single-channel dereverberation techniques and objective speech quality as well as speech intelligibility measures are analyzed and discussed. Six different single-channel dereverberation algorithms were included in the evaluation to account for different types of distortions. The subjective quality was assessed along the four attributes reverberant, colored, distorted and overall quality following the recommendations of ITU-T P.835. The objective measures included system-based, i.e. channel-based, as well as signal-based measures.