This paper presents a system aiming at joint dereverberation and noise reduction by applying a combination of a beamformer with a single-channel spectral enhancement scheme. First, a minimum variance distortionless response beamformer with an online estimated noise coherence matrix is used to suppress noise and reverberation. The output of this beamformer is then processed by a single-channel spectral enhancement scheme, based on statistical room acoustics, minimum statistics, and temporal cepstrum smoothing, to suppress residual noise and reverberation. The evaluation is conducted using the REVERB challenge corpus, designed to evaluate speech enhancement algorithms in the presence of both reverberation and noise. The proposed system is evaluated using instrumental speech quality measures, the performance of an automatic speech recognition system, and a subjective evaluation of the speech quality based on a MUSHRA test. The performance achieved by beamforming, single-channel spectral enhancement, and their combination are compared, and experimental results show that the proposed system is effective in suppressing both reverberation and noise while improving the speech quality. The achieved improvements are particularly significant in conditions with high reverberation times.

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.

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).

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 identific

Algorithms for the automatic detection and recognition of acoustic events are increasingly gaining relevance for the reliable and robust functioning of consumer, assistive and monitoring systems. The extraction of appropriate task relevant acoustic features from the raw sound signal clearly influences performance of subsequent statistical classification, in particular in adverse acoustic situations. The present contribution investigates the use of biologically-inspired features, derived from a filterbank of two-dimensional Gabor functions, that decompose the spectro-temporal power density into components which capture spectral, temporal and joint spectro-temporal modulation patterns. It is hypothesized that the comparably large joint spectral and temporal extent of these Gabor functions results in features that allow for robust classification. Evaluation of the proposed feature extraction scheme together with an hidden Markov model (HMM) classifier is conducted on two corpora comprising acoustic events in realistic adverse conditions from the D-CASE and CLEAR'07 evaluation campaigns. Relevance of each Gabor filter for classification is analyzed and an optimized parameter set for the Gabor filterbank (GFB) is identified. Performance of the optimized GFB is evaluated in comparison to other state-of-the-art algorithms on isolated event classification and on the full acoustic event detection (AED) including joint classification and temporal segmentation of events. Results show that Gabor features result in a signal representation that exhibits separated average class-specific patterns. An improvement in classification accuracy of up to 26% relative to the Mel-frequency cepstral coefficient (MFCC) baseline is obtained with the optimized GFB. Further experiments demonstrate that this improvement cannot be explained by purely temporal or purely spectral Gabor basis functions. Rather, a GFB with features extending in joint spectro-temporal directions is required to obtain optimum performance. Performance on AED with the D-CASE challenge dataset is shown to improve on previous algorithms from the recent literature.

Many signal processing algorithms have been proposed to improve the quality of speech recorded in the presence of noise and reverberation. Perceptual measures, i.e., listening tests, are usually considered the most reliable way to evaluate the quality of speech processed by such algorithms but are costly and time-consuming. Consequently, speech enhancement algorithms are often evaluated using signal-based measures, which can be either intrusive or non-intrusive. As the computation of intrusive measures requires a reference signal, only non-intrusive measures can be used in applications for which the clean speech signal is not available. However, many existing non-intrusive measures correlate poorly with the perceived speech quality, particularly when applied over a wide range of algorithms or acoustic conditions. In this paper, we propose a novel non-intrusive measure of the quality of processed speech that combines modulation energy features and a recurrent neural network using long short-term memory cells. We collected a dataset of perceptually evaluated signals representing several acoustic conditions and algorithms and used this dataset to train and evaluate the proposed measure. Results show that the proposed measure yields higher correlation with perceptual speech quality than that of benchmark intrusive and non-intrusive measures when considering various categories of algorithms. Although the proposed measure is sensitive to mismatch between training and testing, results show that it is a useful approach to evaluate specific algorithms over a wide range of acoustic conditions and may, thus, become particularly useful for real-time selection of speech enhancement algorithm settings.