scholarly journals Singing Voice Detection in Opera Recordings: A Case Study on Robustness and Generalization

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1214
Author(s):  
Michael Krause ◽  
Meinard Müller ◽  
Christof Weiß
Keyword(s):  
Machine Learning ◽  
Traditional Approach ◽  
Training Dataset ◽  
Singing Voice ◽  
Audio Recordings ◽  
Voice Detection ◽  
Music Information ◽  
Music Audio ◽  
Recorded Performances

Automatically detecting the presence of singing in music audio recordings is a central task within music information retrieval. While modern machine-learning systems produce high-quality results on this task, the reported experiments are usually limited to popular music and the trained systems often overfit to confounding factors. In this paper, we aim to gain a deeper understanding of such machine-learning methods and investigate their robustness in a challenging opera scenario. To this end, we compare two state-of-the-art methods for singing voice detection based on supervised learning: A traditional approach relying on hand-crafted features with a random forest classifier, as well as a deep-learning approach relying on convolutional neural networks. To evaluate these algorithms, we make use of a cross-version dataset comprising 16 recorded performances (versions) of Richard Wagner’s four-opera cycle Der Ring des Nibelungen. This scenario allows us to systematically investigate generalization to unseen versions, musical works, or both. In particular, we study the trained systems’ robustness depending on the acoustic and musical variety, as well as the overall size of the training dataset. Our experiments show that both systems can robustly detect singing voice in opera recordings even when trained on relatively small datasets with little variety.

scholarly journals Machine Learning Generalisation across Different 3D Architectural Heritage

2020 ◽  
Vol 9 (6) ◽  
pp. 379 ◽  
Author(s):  
Eleonora Grilli ◽  
Fabio Remondino
Keyword(s):  
Machine Learning ◽  
Point Cloud ◽  
Machine Learning Techniques ◽  
Training Dataset ◽  
High Complexity ◽  
Architectural Heritage ◽  
Learning Techniques ◽  
Machine Learning Model ◽  
Point Cloud Classification

The use of machine learning techniques for point cloud classification has been investigated extensively in the last decade in the geospatial community, while in the cultural heritage field it has only recently started to be explored. The high complexity and heterogeneity of 3D heritage data, the diversity of the possible scenarios, and the different classification purposes that each case study might present, makes it difficult to realise a large training dataset for learning purposes. An important practical issue that has not been explored yet, is the application of a single machine learning model across large and different architectural datasets. This paper tackles this issue presenting a methodology able to successfully generalise to unseen scenarios a random forest model trained on a specific dataset. This is achieved looking for the best features suitable to identify the classes of interest (e.g., wall, windows, roof and columns).

scholarly journals On the Inapplicability of Supervised Machine Learning to Evolutionary Studies

2020 ◽  
Author(s):  
Eran Elhaik ◽  
Dan Graur
Keyword(s):  
Machine Learning ◽  
A Priori ◽  
Supervised Machine Learning ◽  
Training Dataset ◽  
The Bible ◽  
Human Genomes ◽  
Evolutionary Studies ◽  
Two Factors ◽  
Negative Controls

Supervised machine learning (SML) is a powerful method for predicting a small number of well-defined output groups (e.g., potential buyers of a certain product) by taking as input a large number of known well-defined measurements (e.g., past purchases, income, ethnicity, gender, credit record, age, favorite color, favorite chewing gum). SML is predicated upon the existence of a training dataset in which the correspondence between the input and output is known to be true. SML has had enormous success in the world of commerce, and this success has prompted a few scientists to employ it in the study of molecular and genome evolution. Here, we list the properties of SML that make it an unsuitable tool in evolutionary studies. In particular, we argue that SML cannot be used in an evolutionary exploratory context for the simple reason that training datasets that are known to be a priori true do not exist. As a case study, we use an SML study in which it was concluded that most human genomes evolve by positive selection through soft selective sweeps (Schrider and Kern 2017). We show that in the absence of legitimate training datasets, Schrider and Kern (2017) used (1) simulations that employ many manipulatable variables and (2) a system of cherry-picking data that would put to shame most modern evangelical exegeses of the Bible. These two factors, in addition to the lack of methodological detail and the lack of either negative controls or corrections for multiple comparisons, lead us to conclude that all evolutionary inferences derived from so-called SML algorithms (e.g., discoal) should be taken with a huge shovel of salt.

scholarly journals On the Inapplicability of Supervised Machine Learning to Studying the Driving Forces of Evolution

2021 ◽  
Author(s):  
Eran Elhaik ◽  
Dan Graur
Keyword(s):  
Machine Learning ◽  
Driving Forces ◽  
A Priori ◽  
Supervised Machine Learning ◽  
Training Dataset ◽  
The Bible ◽  
Human Genomes ◽  
Two Factors ◽  
Negative Controls

Supervised machine learning (SML) is a powerful method for predicting a small number of well-defined output groups (e.g., potential buyers of a certain product) by taking as input a large number of known well-defined measurements (e.g., past purchases, income, ethnicity, gender, credit record, age, favorite color, favorite chewing gum). SML is predicated upon the existence of a training dataset in which the correspondence between the input and output is known to be true. SML has had enormous success in the world of commerce, and this success may have prompted a few scientists to employ it in the study of molecular and genome evolution. Here, we list the properties of SML that make it an unsuitable tool in certain evolutionary studies. In particular, we argue that SML cannot be used in an evolutionary exploratory context for the simple reason that training datasets that are known to be a priori true do not exist. As a case study, we use an SML study in which it was concluded that most human genomes evolve by positive selection through soft selective sweeps (Schrider and Kern 2017). We show that in the absence of legitimate training datasets, Schrider and Kern (2017) used (1) simulations that employ many manipulatable variables and (2) a system of cherry-picking data that would put to shame most modern evangelical exegeses of the Bible. These two factors, in addition to the lack of methodological detail and negative controls, lead us to conclude that all evolutionary inferences derived from so-called SML algorithms (e.g., S-HIC) should be taken with a huge shovel of salt.

scholarly journals SELM: Software Engineering of Machine Learning Models

2021 ◽  
Author(s):  
Nafiseh Jafari ◽  
Mohammad Reza Besharati ◽  
Maryam Hourali
Keyword(s):  
Machine Learning ◽  
Software Engineering ◽  
Interdisciplinary Approach ◽  
Interdisciplinary Teams ◽  
Process Efficiency ◽  
Training Dataset ◽  
Learning Models ◽  
Machine Learning Model ◽  
Machine Learning Models

One of the pillars of any machine learning model is its concepts. Using software engineering, we can engineer these concepts and then develop and expand them. In this article, we present a SELM framework for Software Engineering of machine Learning Models. We then evaluate this framework through a case study. Using the SELM framework, we can improve a machine learning process efficiency and provide more accuracy in learning with less processing hardware resources and a smaller training dataset. This issue highlights the importance of an interdisciplinary approach to machine learning. Therefore, in this article, we have provided interdisciplinary teams’ proposals for machine learning.

AN EFFICIENT MACHINE LEARNING MODEL FOR PREDICTION OF ACUTE MYOCARDIAL INFARCTION

2020 ◽  
Vol 13 ◽  
Author(s):  
Dhilsath Fathima.M ◽  
S. Justin Samuel ◽  
R. Hari Haran
Keyword(s):  
Machine Learning ◽  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Logistic Regression ◽  
Decision Tree ◽  
Learning Model ◽  
Training Dataset ◽  
Data Set ◽  
Machine Learning Model ◽  
Proposed Model

Aim: This proposed work is used to develop an improved and robust machine learning model for predicting Myocardial Infarction (MI) could have substantial clinical impact. Objectives: This paper explains how to build machine learning based computer-aided analysis system for an early and accurate prediction of Myocardial Infarction (MI) which utilizes framingham heart study dataset for validation and evaluation. This proposed computer-aided analysis model will support medical professionals to predict myocardial infarction proficiently. Methods: The proposed model utilize the mean imputation to remove the missing values from the data set, then applied principal component analysis to extract the optimal features from the data set to enhance the performance of the classifiers. After PCA, the reduced features are partitioned into training dataset and testing dataset where 70% of the training dataset are given as an input to the four well-liked classifiers as support vector machine, k-nearest neighbor, logistic regression and decision tree to train the classifiers and 30% of test dataset is used to evaluate an output of machine learning model using performance metrics as confusion matrix, classifier accuracy, precision, sensitivity, F1-score, AUC-ROC curve. Results: Output of the classifiers are evaluated using performance measures and we observed that logistic regression provides high accuracy than K-NN, SVM, decision tree classifiers and PCA performs sound as a good feature extraction method to enhance the performance of proposed model. From these analyses, we conclude that logistic regression having good mean accuracy level and standard deviation accuracy compared with the other three algorithms. AUC-ROC curve of the proposed classifiers is analyzed from the output figure.4, figure.5 that logistic regression exhibits good AUC-ROC score, i.e. around 70% compared to k-NN and decision tree algorithm. Conclusion: From the result analysis, we infer that this proposed machine learning model will act as an optimal decision making system to predict the acute myocardial infarction at an early stage than an existing machine learning based prediction models and it is capable to predict the presence of an acute myocardial Infarction with human using the heart disease risk factors, in order to decide when to start lifestyle modification and medical treatment to prevent the heart disease.

Derivation of Respiratory Metrics in Health and Asthma; Machine Learning Methodology (Preprint)

2020 ◽  
Author(s):  
Joseph Prinable ◽  
Peter Jones ◽  
David Boland ◽  
Alistair McEwan ◽  
Cindy Thamrin
Keyword(s):  
Machine Learning ◽  
Short Term Memory ◽  
Reference Signal ◽  
Machine Learning Algorithms ◽  
Training Dataset ◽  
Local Health ◽  
Strongly Correlated ◽  
Human Research Ethics ◽  
Expiration Time ◽  
Wide Variability

BACKGROUND The ability to continuously monitor breathing metrics may have indications for general health as well as respiratory conditions such as asthma. However, few studies have focused on breathing due to a lack of available wearable technologies. OBJECTIVE Examine the performance of two machine learning algorithms in extracting breathing metrics from a finger-based pulse oximeter, which is amenable to long-term monitoring. METHODS Pulse oximetry data was collected from 11 healthy and 11 asthma subjects who breathed at a range of controlled respiratory rates. UNET and Long Short-Term memory (LSTM) algorithms were applied to the data, and results compared against breathing metrics derived from respiratory inductance plethysmography measured simultaneously as a reference. RESULTS The UNET vs LSTM model provided breathing metrics which were strongly correlated with those from the reference signal (all p<0.001, except for inspiratory:expiratory ratio). The following relative mean bias(95% confidence interval) were observed: inspiration time 1.89(-52.95, 56.74)% vs 1.30(-52.15, 54.74)%, expiration time -3.70(-55.21, 47.80)% vs -4.97(-56.84, 46.89)%, inspiratory:expiratory ratio -4.65(-87.18, 77.88)% vs -5.30(-87.07, 76.47)%, inter-breath intervals -2.39(-32.76, 27.97)% vs -3.16(-33.69, 27.36)%, and respiratory rate 2.99(-27.04 to 33.02)% vs 3.69(-27.17 to 34.56)%. CONCLUSIONS Both machine learning models show strongly correlation and good comparability with reference, with low bias though wide variability for deriving breathing metrics in asthma and health cohorts. Future efforts should focus on improvement of performance of these models, e.g. by increasing the size of the training dataset at the lower breathing rates. CLINICALTRIAL Sydney Local Health District Human Research Ethics Committee (#LNR\16\HAWKE99 ethics approval).

Digging for the truth: the case for active annotation in evaluating the credibility of online medical information (Preprint)

2020 ◽  
Author(s):  
Mikołaj Morzy ◽  
Bartłomiej Balcerzak ◽  
Adam Wierzbicki ◽  
Adam Wierzbicki
Keyword(s):  
Machine Learning ◽  
Medical Information ◽  
Representation Learning ◽  
Training Dataset ◽  
Highly Qualified ◽  
Human In The Loop ◽  
Annotation Process ◽  
Comprehensive Framework ◽  
Online Sources ◽  
The Web

BACKGROUND With the rapidly accelerating spread of dissemination of false medical information on the Web, the task of establishing the credibility of online sources of medical information becomes a pressing necessity. The sheer number of websites offering questionable medical information presented as reliable and actionable suggestions with possibly harmful effects poses an additional requirement for potential solutions, as they have to scale to the size of the problem. Machine learning is one such solution which, when properly deployed, can be an effective tool in fighting medical disinformation on the Web. OBJECTIVE We present a comprehensive framework for designing and curating of machine learning training datasets for online medical information credibility assessment. We show how the annotation process should be constructed and what pitfalls should be avoided. Our main objective is to provide researchers from medical and computer science communities with guidelines on how to construct datasets for machine learning models for various areas of medical information wars. METHODS The key component of our approach is the active annotation process. We begin by outlining the annotation protocol for the curation of high-quality training dataset, which then can be augmented and rapidly extended by employing the human-in-the-loop paradigm to machine learning training. To circumvent the cold start problem of insufficient gold standard annotations, we propose a pre-processing pipeline consisting of representation learning, clustering, and re-ranking of sentences for the acceleration of the training process and the optimization of human resources involved in the annotation. RESULTS We collect over 10 000 annotations of sentences related to selected subjects (psychiatry, cholesterol, autism, antibiotics, vaccines, steroids, birth methods, food allergy testing) for less than $7 000 employing 9 highly qualified annotators (certified medical professionals) and we release this dataset to the general public. We develop an active annotation framework for more efficient annotation of non-credible medical statements. The results of the qualitative analysis support our claims of the efficacy of the presented method. CONCLUSIONS A set of very diverse incentives is driving the widespread dissemination of medical disinformation on the Web. An effective strategy of countering this spread is to use machine learning for automatically establishing the credibility of online medical information. This, however, requires a thoughtful design of the training pipeline. In this paper we present a comprehensive framework of active annotation. In addition, we publish a large curated dataset of medical statements labelled as credible, non-credible, or neutral.

Opera and the South African Political

2019 ◽  
pp. 289-311
Author(s):  
Christopher Ballantine
Keyword(s):  
South Africa ◽  
South African ◽  
Singing Voice ◽  
The South ◽  
Sociopolitical Context ◽  
Creating Meaning ◽  
Empirical Means

Christopher Ballantine’s focus is on timbre, in particular the timbre of the singing voice, and how this combines with the imagination to create meaning. His investigation is largely philosophical; but the growth in popularity of opera in post-apartheid South Africa provides empirical means for Ballantine to indicate this powerful but analytically neglected way of creating meaning in the performance of music. His case study shows how timbre can produce musical experiences that have a particular, and often surprising, resonance. Through interviews with leading figures in South African opera, Ballantine demonstrates that timbre is a vital wellspring of imagined meaning; it should especially be seen thus if we seek to understand the singing voice in a sociopolitical context such as that of South Africa during and after apartheid.

Sign in / Sign up

Export Citation Format

Share Document