Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Digital processing of speech signals

This book is about relations between three different areas of mathematics and theoretical computer science: combinatorial group theory, cryptography, and complexity theory. It explores how non-commutative (infinite) groups, which are typically studied in combinatorial group theory, can be used in public-key cryptography. It also shows that there is remarkable feedback from cryptography to combinatorial group theory because some of the problems motivated by cryptography appear to be new to group theory, and they open many interesting research avenues within group theory. In particular, a lot of emphasis in the book is put on studying search problems, as compared to decision problems traditionally studied in combinatorial group theory. Then, complexity theory, notably generic-case complexity of algorithms, is employed for cryptanalysis of various cryptographic protocols based on infinite groups, and the ideas and machinery from the theory of generic-case complexity are used to study asymptotically dominant properties of some infinite groups that have been applied in public-key cryptography so far. This book also describes new interesting developments in the algorithmic theory of solvable groups and another spectacular new development related to complexity of group-theoretic problems, which is based on the ideas of compressed words and straight-line programs coming from computer science.

Non-Commutative Cryptography and Complexity of Group-Theoretic Problems

The INTERSPEECH 2020 Computational Paralinguistics Challenge addresses three different problems for the first time in a
research competition under well-defined conditions: In the Elderly Emotion Sub-Challenge, arousal and valence in the speech
of elderly individuals have to be modelled as a 3-class problem;
in the Breathing Sub-Challenge, breathing has to be assessed as a
regression problem; and in the Mask Sub-Challenge, speech without and with a surgical mask has to be told apart. We describe
the Sub-Challenges, baseline feature extraction, and classifiers
based on the ‘usual’ COMPARE and BoAW features as well as
deep unsupervised representation learning using the AUDEEP
toolkit, and deep feature extraction from pre-trained CNNs using
the DEEP SPECTRUM toolkit; in addition, we partially add deep
end-to-end sequential modelling, and, for the first time in the
challenge, linguistic analysis

/pdf/the-interspeech-2020-computational-paralinguistics-challenge-71hgoysxus.pdf

The INTERSPEECH 2020 Computational Paralinguistics Challenge: Elderly Emotion, Breathing & Masks.

Methods employ sensors in portable devices (e.g., smartphones) both to sense content information (e.g., audio and imagery) and context information. Device processing is desirably dependent on both. For example, some embodiments activate certain processor intensive operations (e.g., content recognition) based on classification of sensed content and context. The context can control the location where information produced from such operations is stored, or control an alert signal indicating, e.g., that sensed speech is being transcribed. Some arrangements post sensor data collected by one device to a cloud repository, for access and processing by other devices. Multiple devices can collaborate in collecting and processing data, to exploit advantages each may have (e.g., in location, processing ability, social network resources, etc.). A great many other features and arrangements are also detailed.

Context-based smartphone sensor logic

We present an efficient algorithm for segmentation of audio signals into speech or music. The central motivation to our study is consumer audio applications, where various real-time enhancements are often applied. The algorithm consists of a learning phase and a classification phase. In the learning phase, predefined training data is used for computing various time-domain and frequency-domain features, for speech and music signals separately, and estimating the optimal speech/music thresholds, based on the probability density functions of the features. An automatic procedure is employed to select the best features for separation. In the test phase, initial classification is performed for each segment of the audio signal, using a three-stage sieve-like approach, applying both Bayesian and rule-based methods. To avoid erroneous rapid alternations in the classification, a smoothing technique is applied, averaging the decision on each segment with past segment decisions. Extensive evaluation of the algorithm, on a database of more than 12 hours of speech and more than 22 hours of music showed correct identification rates of 99.4% and 97.8%, respectively, and quick adjustment to alternating speech/music sections. In addition to its accuracy and robustness, the algorithm can be easily adapted to different audio types, and is suitable for real-time operation.

/pdf/a-decision-tree-based-algorithm-for-speech-music-ia1mn0uza0.pdf

A decision-tree-based algorithm for speech/music classification and segmentation

Automatic detection of predefined events in speech and audio signals is a challenging and promising subject in signal processing. One important application of such detection is removal or suppression of unwanted sounds in audio recordings, for instance in the professional music industry, where the demand for quality is very high. Breath sounds, which are present in most song recordings and often degrade the aesthetic quality of the voice, are an example of such unwanted sounds. Another example is bad pronunciation of certain phonemes. In this paper, we present an automatic algorithm for accurate detection of breaths in speech or song signals. The algorithm is based on a template matching approach, and consists of three phases. In the first phase, a template is constructed from mel frequency cepstral coefficients (MFCCs) matrices of several breath examples and their singular value decompositions, to capture the characteristics of a typical breath event. Next, in the initial processing phase, each short-time frame is compared to the breath template, and marked as breathy or nonbreathy according to predefined thresholds. Finally, an edge detection algorithm, based on various time-domain and frequency-domain parameters, is applied to demarcate the exact boundaries of each breath event and to eliminate possible false detections. Evaluation of the algorithm on a database of speech and songs containing several hundred breath sounds yielded a correct identification rate of 98% with a specificity of 96%

An Effective Algorithm for Automatic Detection and Exact Demarcation of Breath Sounds in Speech and Song Signals

Automatic detection of a baby cry in audio signals is an essential step in applications such as remote baby monitoring. It is also important for researchers, who study the relation between baby cry patterns and various health or developmental parameters. In this paper, we propose two machine-learning algorithms for automatic detection of baby cry in audio recordings. The first algorithm is a low-complexity logistic regression classifier, used as a reference. To train this classifier, we extract features such as Mel-frequency cepstrum coefficients, pitch and formants from the recordings. The second algorithm uses a dedicated convolutional neural network (CNN), operating on log Mel-filter bank representation of the recordings. Performance evaluation of the algorithms is carried out using an annotated database containing recordings of babies (0-6 months old) in domestic environments. In addition to baby cry, these recordings contain various types of domestic sounds, such as parents talking and door opening. The CNN classifier is shown to yield considerably better results compared to the logistic regression classifier, demonstrating the power of deep learning when applied to audio processing.

/pdf/baby-cry-detection-in-domestic-environment-using-deep-549rtpju65.pdf

Baby Cry Detection in Domestic Environment Using Deep Learning

Automatic detection of a baby cry in audio signals is an essential step in applications such as remote baby monitoring. It is also important for researchers, who study the relation between baby cry patterns and various health or developmental parameters. In this paper, we propose two machine-learning algorithms for automatic detection of baby cry in audio recordings. The first algorithm is a low-complexity logistic regression classifier, used as a reference. To train this classifier, we extract features such as Mel-frequency cepstrum coefficients, pitch and formants from the recordings. The second algorithm uses a dedicated convolutional neural network (CNN), operating on log Mel-filter bank representation of the recordings. Performance evaluation of the algorithms is carried out using an annotated database containing recordings of babies (0–6 months old) in domestic environments. In addition to baby cry, these recordings contain various types of domestic sounds, such as parents talking and door opening. The CNN classifier is shown to yield considerably better results compared to the logistic regression classifier, demonstrating the power of deep learning when applied to audio processing.

/pdf/baby-cry-detection-in-domestic-environment-using-deep-4xriiivs2j.pdf

Baby cry detection in domestic environment using deep learning

An apparatus for classifying an input audio signal into audio contents of a first and second class, comprising an audio segmentation module adapted to segment said input audio signal into segments of a predetermined length; a feature computation module adapted to calculate for the segments features characterizing said audio input signal; a threshold comparison module adapted to generate a feature vector for each of said one or more segments based on a plurality of predetermined thresholds, the thresholds including for each of the audio contents of the first class and of the second class a substantially near certainty threshold, a substantially high certainty threshold, and a substantially low certainty threshold; and a classification module adapted to analyze the feature vector and classify each one of said one or more segments as audio contents of the first class, of the second class, or as non-decisive audio contents.

Dima Ruinskiy

Papers

A decision-tree-based algorithm for speech/music classification and segmentation

An Effective Algorithm for Automatic Detection and Exact Demarcation of Breath Sounds in Speech and Song Signals

Baby Cry Detection in Domestic Environment Using Deep Learning

Baby cry detection in domestic environment using deep learning

Apparatus and method for classification and segmentation of audio content, based on the audio signal