In low-resource scenarios, for example, small datasets or a lack in computational resources available, state-of-the-art deep learning methods for speech recognition have been known to fail. It is possible to achieve more robust models if care is taken to ensure the learning guarantees provided by the statistical learning theory. This work presents a shallow and hybrid approach using a convolutional neural network feature extractor fed into a hierarchical tree of support vector machines for classification. Here, we show that gross errors present even in state-of-the-art systems can be avoided and that an accurate acoustic model can be built in a hierarchical fashion. Furthermore, we present proof that our algorithm does adhere to the learning guarantees provided by the statistical learning theory. The acoustic model produced in this work outperforms traditional hidden Markov models, and the hierarchical support vector machine tree outperforms a multi-class multilayer perceptron classifier using the same features. More importantly, we isolate the performance of the acoustic model and provide results on both the frame and phoneme level, considering the true robustness of the model. We show that even with a small amount of data, accurate and robust recognition rates can be obtained.

/pdf/theoretical-learning-guarantees-applied-to-acoustic-modeling-2p5tuzf1m4.pdf

Theoretical learning guarantees applied to acoustic modeling

This chapter starts by describing the necessary concepts and assumptions to ensure supervised learning. Later on, it details the Empirical Risk Minimization (ERM) principle, which is the key point for the Statistical Learning Theory (SLT). The ERM principle provides upper bounds to make the empirical risk a good estimator for the expected risk, given the bias of some learning algorithm. This bound is the main theoretical tool to provide learning guarantees for classification tasks. Afterwards, other useful tools and concepts are introduced.

Statistical Learning Theory

SHULBY, C. D. RAMBLE: robust acoustic modeling for Brazilian learners of English. 2018. 160 p. Tese (Doutorado em Ciências – Ciências de Computação e Matemática Computacional) – Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo, São Carlos – SP, 2018. The gains made by current deep-learning techniques have often come with the price tag of big data and where that data is not available, a new solution must be found. Such is the case for accented and noisy speech where large databases do not exist and data augmentation techniques, which are less than perfect, present an even larger obstacle. Another problem is that state-of-the-art results are rarely reproducible because they use proprietary datasets, pretrained networks and/or weight initializations from other larger networks. An example of a low resource scenario exists even in the fifth largest land in the world; home to most of the speakers of the seventh most spoken language on earth. Brazil is the leader in the Latin-American economy and as a BRIC country aspires to become an ever-stronger player in the global marketplace. Still, English proficiency is low, even for professionals in businesses and universities. Low intelligibility and strong accents can damage professional credibility. It has been established in the literature for foreign language teaching that it is important that adult learners are made aware of their errors as outlined by the “Noticing Theory”, explaining that a learner is more successful when he is able to learn from his own mistakes. An essential objective of this dissertation is to classify phonemes in the acoustic model which is needed to properly identify phonemic errors automatically. A common belief in the community is that deep learning requires large datasets to be effective. This happens because brute force methods create a highly complex hypothesis space which requires large and complex networks which in turn demand a great amount of data samples in order to generate useful networks. Besides that, the loss functions used in neural learning does not provide statistical learning guarantees and only guarantees the network can memorize the training space well. In the case of accented or noisy speech where a new sample can carry a great deal of variation from the training samples, the generalization of such models suffers. The main objective of this dissertation is to investigate how more robust acoustic generalizations can be made, even with little data and noisy accented-speech data. The approach here is to take advantage of raw feature extraction provided by deep learning techniques and instead focus on how learning guarantees can be provided for small datasets to produce robust results for acoustic modeling without the dependency of big data. This has been done by careful and intelligent parameter and architecture selection within the framework of the statistical learning theory. Here, an intelligently defined CNN architecture, together with context windows and a knowledge-driven hierarchical tree of SVM classifiers achieves nearly state-of-the-art frame-wise phoneme recognition results with absolutely no pretraining or external weight initialization. A goal of this thesis is to produce transparent and reproducible architectures with high frame-level accuracy, comparable to the state of the art. Additionally, a convergence analysis based on the learning guarantees of the statistical learning theory is performed in order to evidence the generalization capacity of the model. The model achieves 39.7% error in framewise classification and a 43.5% phone error rate using deep feature extraction and SVM classification even with little data (less than 7 hours). These results are comparable to studies which use well over ten times that amount of data. Beyond the intrinsic evaluation, the model also achieves an accuracy of 88% in the identification of epenthesis, the error which is most difficult for Brazilian speakers of English This is a 69% relative percentage gain over the previous values in the literature. The results are significant because it shows how deep feature extraction can be applied to little data scenarios, contrary to popular belief. The extrinsic, task-based results also show how this approach could be useful in tasks like automatic error diagnosis. Another contribution is the publication of a number of freely available resources which previously did not exist, meant to aid future researches in dataset creation.

/pdf/ramble-robust-acoustic-modeling-for-brazilian-learners-of-mt3zr5f2ho.pdf

RAMBLE: robust acoustic modeling for Brazilian learners of English

Unlabelled data appear in many domains and are particularly relevant to streaming applications, where even though data is abundant, labelled data is rare. To address the learning problems associated with such data, one can ignore the unlabelled data and focus only on the labelled data (supervised learning); use the labelled data and attempt to leverage the unlabelled data (semi-supervised learning); or assume some labels will be available on request (active learning). The first approach is the simplest, yet the amount of labelled data available will limit the predictive performance. The second relies on finding and exploiting the underlying characteristics of the data distribution. The third depends on an external agent to provide the required labels in a timely fashion. This survey pays special attention to methods that leverage unlabelled data in a semi-supervised setting. We also discuss the delayed labelling issue, which impacts both fully supervised and semi-supervised methods. We propose a unified problem setting, discuss the learning guarantees and existing methods, explain the differences between related problem settings. Finally, we review the current benchmarking practices and propose adaptations to enhance them.

A Survey on Semi-Supervised Learning for Delayed Partially Labelled Data Streams.

Machine Learning (ML) is widely used to automatically extract meaningful information from Electronic Health Records (EHR) to support operational, clinical, and financial decision-making. However, ML models require a large number of annotated examples to provide satisfactory results, which is not possible in most healthcare scenarios due to the high cost of clinician-labeled data. Active Learning (AL) is a process of selecting the most informative instances to be labeled by an expert to further train a supervised algorithm. We demonstrate the effectiveness of AL in multi-label text classification in the clinical domain. In this context, we apply a set of well-known AL methods to help automatically assign ICD-9 codes on the MIMIC-III dataset. Our results show that the selection of informative instances provides satisfactory classification with a significantly reduced training set (8.3\% of the total instances). We conclude that AL methods can significantly reduce the manual annotation cost while preserving model performance.

Active learning for medical code assignment.

The Statistical Learning Theory (SLT) provides the theoretical guarantees for supervised machine learning based on the Empirical Risk Minimization Principle (ERMP). Such principle defines an upper bound to ensure the uniform convergence of the empirical risk Remp(f), i.e., the error measured on a given data sample, to the expected value of risk R(f) (a.k.a. actual risk), which depends on the Joint Probability Distribution P(X x Y) mapping input examples x in X to class labels y in Y. The uniform convergence is only ensured when the Shattering coefficient N(F,2n) has a polynomial growing behavior. This paper proves the Shattering coefficient for any Hilbert space H containing the input space X and discusses its effects in terms of learning guarantees for supervised machine algorithms.

Computing the Shattering Coefficient of Supervised Learning Algorithms.

The data clustering problem is of central importance for the area of machine learning, given its usefulness to represent data structural similarities from input spaces. Although, data clustering counts on scarse literature of a theoretical framework with generalization guarantees. In this context, this manuscript introduces a new concept, based on multidimensional persistent homology, to analyze the conditions on which a clustering model is capable of generalizing data. As a first step, we propose a more general definition of DC problem by relying on topological spaces, instead of metric ones as typically approached in the literature. From that, we show that the data clustering problem presents an analogous dilemma to the bias-variance one, which is here referred to as the coarse-refinement dilemma, from which we conclude that: (i) highly-refined partitions and the clustering instability (overfitting); and (ii) over-coarse partitions and the lack of representativeness (underfitting). The coarse-refinement dilemma suggests the need of a relaxation of Kleinberg’s richness axiom, as such axiom allows the production of unstable or unrepresentative partitions. Experimental exploration considering different clustering refinements can, then, depict such partitions.

https://www.teses.usp.br/teses/disponiveis/55/55134/tde-18112020-130229/publico/YuleVaz_revisada.pdf

Carlos Henrique Grossi Ferreira

Papers

Computing the Shattering Coefficient of Supervised Learning Algorithms.

Coarse-refinement dilemma: On generalization bounds for data clustering