Acoustic features and machine learning models have been recently proposed as promising tools to analyze lessons. Furthermore, acoustic patterns, both in the time and spectral domain, have been found to be related to teacher pedagogical practices. Nonetheless, most of previous work relies on expensive or third party equipment, limiting its scalability, and additionally, it is mainly used for diarization. Instead, in this work we present a cost-effective approach to identify teachers’ practices according to three categories (Presenting, Administration, and Guiding) which are compiled from the Classroom Observation Protocol for Undergraduate STEM. Particularly, we record teachers’ lessons using low-cost microphones connected to their smartphones. We then compute the mean and standard deviation of the amplitude, Mel spectrogram, and Mel Frequency Cepstral coefficients of the recordings to train supervised models for the task of predicting three categories compiled from the Classroom Observation Protocol for Undergraduate STEM. We found that spectral features perform better at the task of predicting teachers’ activities along the lessons and that our models can predict the presence of the two most common teaching practices with over 80% of accuracy and good discriminative power. Finally, with these models, we found that using audio obtained from the teachers’ smartphones it is also possible to automatically discriminate between sessions where students are using or not an online platform. This approach is important for teachers and other stakeholders who could use an automatic and cost-effective tool for analyzing teaching practices.

In this paper we present a transformation to convert time signals into a randomized low-dimensional vectors such that the inner product between these new features provides information about the similarity of the signals. We show that the described inner product approximates a cross-correlation based kernel. This is very useful at the moment of use Kernel Machines, such as Non-linear Support Vector Machines. Indeed, this allows to apply simpler and faster linear methods on the generated random features. Our proposed scheme improves computational storage and time cost over the direct kernel approach, while performing the classification performance with minimal loss. We support our statements by providing theoretical guarantees as well as empirical evaluation across different data sets.

Speech recordings are a rich source of personal, sensitive data that can be used to support a plethora of diverse applications, from health profiling to biometric recognition. It is therefore essential that speech recordings are adequately protected so that they cannot be misused. Such protection, in the form of privacy-preserving technologies, is required to ensure that: (i) the biometric profiles of a given individual (e.g., across different biometric service operators) are unlinkable; (ii) leaked, encrypted biometric information is irreversible, and that (iii) biometric references are renewable. Whereas many privacy-preserving technologies have been developed for other biometric characteristics, very few solutions have been proposed to protect privacy in the case of speech signals. Despite privacy preservation this is now being mandated by recent European and international data protection regulations. With the aim of fostering progress and collaboration between researchers in the speech, biometrics and applied cryptography communities, this survey article provides an introduction to the field, starting with a legal perspective on privacy preservation in the case of speech data. It then establishes the requirements for effective privacy preservation, reviews generic cryptography-based solutions, followed by specific techniques that are applicable to speaker characterisation (biometric applications) and speech characterisation (non-biometric applications). Glancing at non-biometrics, methods are presented to avoid function creep, preventing the exploitation of biometric information, e.g., to single out an identity in speech-assisted health care via speaker characterisation. In promoting harmonised research, the article also outlines common, empirical evaluation metrics for the assessment of privacy-preserving technologies for speech data.

State of the art acoustic scene classification techniques often employ features of large dimensionality, which are then used to train and perform inferences with kernel machines such as Support Vector Machines. However, the complexity of computing the non-linear kernel matrix for these methods increases with the dimensionality of the features and the size of the dataset. In this work, we introduce a new scheme that hashes features, which combined with a linear function approximates a non-linear Laplacian kernel. Each hash typically has lower dimensionality than the input features and each component is represented by one bit instead of floating values. Hence, allowing efficient computation of the kernel matrix using XOR operations rather than dot-products. Our scheme is demonstrated mathematically and tested in the 2017 DCASE: Acoustic Scene Classification. The hashes reduce up to six powers of two the feature representation with minimal loss of accuracy.

A critically important component of most signal processing procedures is that of computing the distance between signals. In multiparty processing applications where these signals belong to different parties, this introduces privacy challenges. The signals may themselves be private, and the parties to the computation may not be willing to expose them. Solutions proposed to the problem in the literature generally invoke homomorphic encryption schemes, secure multi-party computation, or other cryptographic methods which introduce significant computational complexity into the proceedings, often to the point of making more complex computations requiring repeated computations unfeasible. Other solutions invoke third parties, making unrealistic assumptions about their trustworthiness. In this paper we propose an alternate approach, also based on third party computation, but without assuming as much trust in the third party. Individual participants to the computation “secure” their data through a proposed secure hashing scheme with shared keys, prior to sharing it with the third party. The hashing ensures that the third party cannot recover any information about the individual signals or their statistics, either from analysis of individual computations or their long-term aggregate patterns. We provide theoretical proof of these properties and empirical demonstration of the feasibility of the computation.