Humans have devised a vast array of musical instruments, but the most prevalent instrument remains the human voice. Thus, techniques for applying audio signal processing methods to the singing voice are receiving much attention as the world continues to move toward music-streaming services and as researchers seek to unlock the deep content understanding necessary to enable personalized listening experiences on a large scale. This article provides an introduction to the topic of singing-voice analysis. It surveys the foundations and state of the art in computational modeling across three main categories of singing: general vocalizations, the musical function of voice, and the singing of lyrics. We aim to establish a starting point for practitioners new to this field and frame near-field opportunities and challenges on the horizon.

In this paper, we investigate two deep learning approaches to recovering initial temperature profiles from thermographic images in non-destructive material testing. First, we trained a deep neural network (DNN) in an end-to-end fashion by directly feeding the surface temperature measurements to the DNN. Second, we turned the surface temperature measurements into virtual waves (a recently developed concept in thermography), which we then fed to the DNN. To demonstrate the effectiveness of these methods, we implemented a data generator and created a dataset comprising a total of 100 000 simulated temperature measurement images. With the objective of determining a suitable baseline, we investigated several state-of-the-art model-based reconstruction methods, including Abel transformation, curvelet denoising, and time- and frequency-domain synthetic aperture focusing techniques. Additionally, a physical phantom was created to support evaluation on completely unseen real-world data. The results of several experiments suggest that both the end-to-end and the hybrid approach outperformed the baseline in terms of reconstruction accuracy. The end-to-end approach required the least amount of domain knowledge and was the most computationally efficient one. The hybrid approach required extensive domain knowledge and was more computationally expensive than the end-to-end approach. However, the virtual waves served as meaningful features that convert the complex task of the end-to-end reconstruction into a less demanding undertaking. This in turn yielded better reconstructions with the same number of training samples compared to the end-to-end approach. Additionally, it allowed more compact network architectures and use of prior knowledge, such as sparsity and non-negativity. The proposed method is suitable for non-destructive testing (NDT) in 2D where the amplitudes along the objects are considered to be constant (e.g., for metallic wires). To encourage the development of other deep-learning-based reconstruction techniques, we release both the synthetic and the real-world datasets along with the implementation of the deep learning methods to the research community.

Singing voice detection, also referred to as vocal detection (VD), aims at automatically identifying the regions in a music recording where at least one person sings. It is highly challenging due to the timbral and expressive richness of the human singing voice, as well as the practically endless variety of interfering instrumental accompaniment. Additionally, certain instruments have an inherent risk of being misclassified as vocals due to similarities of the sound production system. In this paper, we present a machine learning approach that is based on our previous work for VD, which is specifically designed to deal with those challenging conditions. The contribution of this paper is threefold: First, we present a new method for VD that passes a compact set of features to a long short-term memory recurrent neural network classifier that obtains state-of-the-art results. Second, we thoroughly evaluate the proposed method along with related approaches to really probe the weaknesses of the methods. In order to allow for such a thorough evaluation, we make a curated collection of datasets available to the research community. Finally, we focus on a specific problem that was not obvious and had not been discussed in the literature so far. The reason for this is precisely because limited evaluations had not revealed this as a problem: the lack of loudness invariance. We will discuss the implications of utilizing loudness-related features and show that our method successfully deals with this problem due to the specific set of features it uses.

The present research proposes a two-step physics- and machine-learning(ML)-based electromechanical impedance (EMI) measurement data evaluation approach for sandwich face layer debonding detection and size estimation in structural health monitoring (SHM) applications. As a case example, a circular aluminum sandwich panel with idealized face layer debonding was used. Both the sensor and debonding were located at the center of the sandwich. Synthetic EMI spectra were generated by a finite-element(FE)-based parameter study, and were used for feature engineering and ML model training and development. Calibration of the real-world EMI measurement data was shown to overcome the FE model simplifications, enabling their evaluation by the found synthetic data-based features and models. The data preprocessing and ML models were validated by unseen real-world EMI measurement data collected in a laboratory environment. The best detection and size estimation performances were found for a One-Class Support Vector Machine and a K-Nearest Neighbor model, respectively, which clearly showed reliable identification of relevant debonding sizes. Furthermore, the approach was shown to be robust against unknown artificial disturbances, and outperformed a previous method for debonding size estimation. The data and code used in this study are provided in their entirety, to enhance comprehensibility, and to encourage future research.