Convolutional recurrent neural networks (CRNs) using convolutional encoder-decoder (CED) structures have shown promising performance for single-channel speech enhancement. These CRNs handle temporal modeling through integrating long short-term memory (LSTM) layers in between convolutional encoder and decoder. However, in such a CRN, the organization of internal representations in feature maps and the focus on local structure of the convolutional mappings has to be discarded for fully-connected LSTM processing. Furthermore, CRNs can be quite restricted concerning the feature space dimension at the input of the LSTM, which, through its fully-connected nature, requires a large amount of trainable parameters. As first novelty, we propose to replace the fully-connected LSTM by a convolutional LSTM (ConvLSTM) and call the resulting network a fully convolutional recurrent network (FCRN). Secondly, since the ConvLSTM retains the structured organization of its input feature maps, we can show that this helps to internally represent the harmonic structure of speech, allowing us to handle high-dimensional input features using less trainable parameters than an LSTM. The proposed FCRN clearly outperforms CRN reference models with similar amounts of trainable parameters in terms of PESQ, STOI, and segmental ΔSNR.

This paper presents an embedded-optimization-based loudspeaker precompensation algorithm using a Hammerstein loudspeaker model, i.e. a cascade of a memoryless nonlinearity and a linear finite impulse response filter. The loudspeaker precompensation consists in a per-frame signal optimization. In order to minimize the perceptible distortion incurred in the loudspeaker, a psychoacoustically motivated optimization criterion is proposed. The resulting per-frame signal optimization problems are solved efficiently using first-order optimization methods. Depending on the invertibility and the smoothness of the memoryless nonlinearity, different first-order optimization methods are proposed and their convergence properties are analyzed. Objective evaluation experiments using synthetic loudspeaker models and real loudspeakers show that the proposed loudspeaker precompensation algorithm provides a significant audio quality improvement, especially so at high playback levels.

The restoration of clipped audio signals, commonly known as declipping, is important to achieve an improved level of audio quality in many audio applications. In this paper, a novel declipping algorithm is presented, jointly based on the theory of compressed sensing (CS) and on well-established properties of human auditory perception. Declipping is formulated as a sparse signal recovery problem using the CS framework. By additionally exploiting knowledge of human auditory perception, a novel perceptual compressed sensing (PCS) framework is devised. A PCS-based declipping algorithm is proposed which uses ℓ1-norm type reconstruction. Comparative objective and subjective evaluation experiments reveal a significant audio quality increase for the proposed PCS-based declipping algorithm compared to CS-based declipping algorithms.

The aim of this paper is to improve the performance of existing speech distortion weighted multi-channel Wiener filter (SDW-MWFμ) based noise reduction (NR) algorithms. It is well known that for the SDW-MWFμthe improved NR performance comes at the cost of higher speech distortion when a fixed speech distortion weighting factor is used. In this paper we propose two psychoacoustically motivated weighting factor selection strategies, devised to exploit masking properties of the human ear. Experimental results based on PESQ scores, SNR improvement, and signal distortion confirm that both proposed psychoacoustically motivated weighting factor selection strategies do improve the NR performance compared to using a fixed weighting factor. In some of the analyzed scenarios, the fixed weighting factor approach is even seen to degrade the PESQ scores, while the psychoacoustically motivated approaches are seen to significantly improve the PESQ scores in all of the analyzed scenarios.

Clipping is an essential signal processing operation in many real-time audio applications, yet the use of existing clipping techniques generally has a detrimental effect on the perceived audio signal quality. In this paper, we present a novel multidisciplinary approach to clipping which aims to explicitly minimize the perceptible clipping-induced distortion by embedding a convex optimization criterion and a psychoacoustic model into a frame-based algorithm. The core of this perception-based clipping algorithm consists in solving a convex optimization problem for each time frame in a fast and reliable way. To this end, three different structure-exploiting optimization methods are derived in the common mathematical framework of convex optimization, and corresponding theoretical complexity bounds are provided. From comparative audio quality evaluation experiments, it is concluded that the perception-based clipping algorithm results in significantly higher objective audio quality scores than existing clipping techniques. Moreover, the algorithm is shown to be capable to adhere to real-time deadlines without making a sacrifice in terms of audio quality.

Clipping is a necessary signal processing operation in many real time audio applications, yet it often reduces the sound quality of the signal. The recently proposed perception-based clipping algorithm has been shown to significantly outperform other clipping techniques in terms of objective sound quality scores. However, the real-time solution of the optimization problems that form the core of this algorithm, poses a challenge. In this paper, a fast gradient projection optimization method is proposed and incorporated into the perception based clipping algorithm. The optimization method will be shown to have an extremely low computational complexity per iteration, allowing the perception-based clipping algorithm to be applied in real-time for a broad range of clipping factors.