CAIR Deep Learning Research Publications

2020

Beukes, J. P., Davel, M. H., & Lotz, S. (2020). Pairwise networks for feature ranking of a geomagnetic storm model. South African Computer Journal, 32(2). http://doi.org/https://doi.org/10.18489/sacj.v32i2.860

Feedforward neural networks provide the basis for complex regression models that produce accurate predictions in a variety of applications. However, they generally do not explicitly provide any information about the utility of each of the input parameters in terms of their contribution to model accuracy. With this is mind, we develop the pairwise network, an adaptation to the fully connected feedforward network that allows the ranking of input parameters according to their contribution to the model output. The application is demonstrated in the context of a space physics problem. Geomagnetic storms are multi-day events characterised by significant perturbations to the magnetic field of the Earth, driven by solar activity. Previous storm forecasting efforts typically use solar wind measurements as input parameters to a regression problem tasked with predicting a perturbation index such as the 1-minute cadence symmetric-H (Sym-H) index. We re-visit the task of predicting Sym-H from solar wind parameters, with two 'twists': (i) Geomagnetic storm phase information is incorporated as model inputs and shown to increase prediction performance. (ii) We describe the pairwise network structure and training process - first validating ranking ability on synthetic data, before using the network to analyse the Sym-H problem.

@article{392,
  author = {Jacques Beukes and Marelie Davel and Stefan Lotz},
  title = {Pairwise networks for feature ranking of a geomagnetic storm model},
  abstract = {Feedforward neural networks provide the basis for complex regression models that produce accurate predictions in a variety of applications. However, they generally do not explicitly provide any information about the utility of each of the input parameters in terms of their contribution to model accuracy. With this is mind, we develop the pairwise network, an adaptation to the fully connected feedforward network that allows the ranking of input parameters according to their contribution to the model output. The application is demonstrated in the context of a space physics problem. Geomagnetic storms are multi-day events characterised by significant perturbations to the magnetic field of the Earth, driven by solar activity. Previous storm forecasting efforts typically use solar wind measurements as input parameters to a regression problem tasked with predicting a perturbation index such as the 1-minute cadence symmetric-H (Sym-H) index. We re-visit the task of predicting Sym-H from solar wind parameters, with two 'twists': (i) Geomagnetic storm phase information is incorporated as model inputs and shown to increase prediction performance. (ii) We describe the pairwise network structure and training process - first validating ranking ability on synthetic data, before using the network to analyse the Sym-H problem.},
  year = {2020},
  journal = {South African Computer Journal},
  volume = {32},
  pages = {35-55},
  issue = {2},
  publisher = {South African Institute of Computer Scientists and Information Technologists},
  isbn = {ISSN: 1015-7999; E:2313-7835},
  doi = {https://doi.org/10.18489/sacj.v32i2.860},
}
Davel, M. H. (2020). Using summary layers to probe neural network behaviour. South African Computer Journal, 32(2). http://doi.org/https://doi.org/10.18489/sacj.v32i2.861

No framework exists that can explain and predict the generalisation ability of deep neural networks in general circumstances. In fact, this question has not been answered for some of the least complicated of neural network architectures: fully-connected feedforward networks with rectified linear activations and a limited number of hidden layers. For such an architecture, we show how adding a summary layer to the network makes it more amenable to analysis, and allows us to define the conditions that are required to guarantee that a set of samples will all be classified correctly. This process does not describe the generalisation behaviour of these networks,but produces a number of metrics that are useful for probing their learning and generalisation behaviour. We support the analytical conclusions with empirical results, both to confirm that the mathematical guarantees hold in practice, and to demonstrate the use of the analysis process.

@article{391,
  author = {Marelie Davel},
  title = {Using summary layers to probe neural network behaviour},
  abstract = {No framework exists that can explain and predict the generalisation ability of deep neural networks in general circumstances. In fact, this question has not been answered for some of the least complicated of neural network architectures: fully-connected feedforward networks with rectified linear activations and a limited number of hidden layers. For such an architecture, we show how adding a summary layer to the network makes it more amenable to analysis, and allows us to define the conditions that are required to guarantee that a set of samples will all be classified correctly. This process does not describe the generalisation behaviour of these networks,but produces a number of metrics that are useful for probing their learning and generalisation behaviour. We support the analytical conclusions with empirical results, both to confirm that the mathematical guarantees hold in practice, and to demonstrate the use of the analysis process.},
  year = {2020},
  journal = {South African Computer Journal},
  volume = {32},
  pages = {102-123},
  issue = {2},
  publisher = {South African Institute of Computer Scientists and Information Technologists},
  isbn = {ISSN: 1015-7999; E:2313-7835},
  url = {http://hdl.handle.net/10394/36916},
  doi = {https://doi.org/10.18489/sacj.v32i2.861},
}
Davel, M. H., Theunissen, M. W., Pretorius, A. P., & Barnard, E. (2020). DNNs as layers of cooperating classifiers. In The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20). New York.

A robust theoretical framework that can describe and predict the generalization ability of deep neural networks (DNNs) in general circumstances remains elusive. Classical attempts have produced complexity metrics that rely heavily on global measures of compactness and capacity with little investigation into the effects of sub-component collaboration. We demonstrate intriguing regularities in the activation patterns of the hidden nodes within fully-connected feedforward networks. By tracing the origin of these patterns, we show how such networks can be viewed as the combination of two information processing systems: one continuous and one discrete. We describe how these two systems arise naturally from the gradient-based optimization process, and demonstrate the classification ability of the two systems, individually and in collaboration. This perspective on DNN classification offers a novel way to think about generalization, in which different subsets of the training data are used to train distinct classifiers; those classifiers are then combined to perform the classification task, and their consistency is crucial for accurate classification.

@{236,
  author = {Marelie Davel and Marthinus Theunissen and Arnold Pretorius and Etienne Barnard},
  title = {DNNs as layers of cooperating classifiers},
  abstract = {A robust theoretical framework that can describe and predict the generalization ability of deep neural networks (DNNs) in general circumstances remains elusive. Classical attempts have produced complexity metrics that rely heavily on global measures of compactness and capacity with little investigation into the effects of sub-component collaboration. We demonstrate intriguing regularities in the activation patterns of the hidden nodes within fully-connected feedforward networks. By tracing the origin of these patterns, we show how such networks can be viewed as the combination of two information processing systems: one continuous and one discrete. We describe how these two systems arise naturally from the gradient-based optimization process, and demonstrate the classification ability of the two systems, individually and in collaboration. This perspective on DNN classification offers a novel way to think about generalization, in which different subsets of the training data are used to train distinct classifiers; those classifiers are then combined to perform the classification task, and their consistency is crucial for accurate classification.},
  year = {2020},
  journal = {The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20)},
  pages = {3725 - 3732},
  month = {07/02-12/02/2020},
  address = {New York},
}
Thirion, J. W. F., Van Heerden, C. J., Giwa, O., & Davel, M. H. (2020). The South African directory enquiries (SADE) name corpus. Language Resources & Evaluation, 54(1). http://doi.org/10.1007/s10579-019-09448-6

We present the design and development of a South African directory enquiries corpus. It contains audio and orthographic transcriptions of a wide range of South African names produced by first-language speakers of four languages, namely Afrikaans, English, isiZulu and Sesotho. Useful as a resource to understand the effect of name language and speaker language on pronunciation, this is the first corpus to also aim to identify the ‘‘intended language’’: an implicit assumption with regard to word origin made by the speaker of the name. We describe the design, collection, annotation, and verification of the corpus. This includes an analysis of the algorithms used to tag the corpus with meta information that may be beneficial to pronunciation modelling tasks.

@article{280,
  author = {Jan Thirion and Charl Van Heerden and Oluwapelumi Giwa and Marelie Davel},
  title = {The South African directory enquiries (SADE) name corpus},
  abstract = {We present the design and development of a South African directory enquiries corpus. It contains audio and orthographic transcriptions of a wide range of South African names produced by first-language speakers of four languages, namely Afrikaans, English, isiZulu and Sesotho. Useful as a resource to understand the effect of name language and speaker language on pronunciation, this is the first corpus to also aim to identify the ‘‘intended language’’: an implicit assumption with regard to word origin made by the speaker of the name. We describe the design, collection, annotation, and verification of the corpus. This includes an analysis of the algorithms used to tag the corpus with meta information that may be beneficial to pronunciation modelling tasks.},
  year = {2020},
  journal = {Language Resources & Evaluation},
  volume = {54},
  pages = {155-184},
  issue = {1},
  publisher = {Springer},
  address = {Cape Town, South Africa},
  doi = {10.1007/s10579-019-09448-6},
}

2019

Lotz, S., Beukes, J. P., & Davel, M. H. (2019). A neural network based method for input parameter selection (Poster). In Machine Learning in Heliophysics. Amsterdam, The Netherlands.

No Abstract

@{368,
  author = {Stefan Lotz and Jacques Beukes and Marelie Davel},
  title = {A neural network based method for input parameter selection (Poster)},
  abstract = {No Abstract},
  year = {2019},
  journal = {Machine Learning in Heliophysics},
  address = {Amsterdam, The Netherlands},
}
Theunissen, M. W., Davel, M. H., & Barnard, E. (2019). Insights regarding overfitting on noise in deep learning. In South African Forum for Artificial Intelligence Research (FAIR). Cape Town, South Africa.

The understanding of generalization in machine learning is in a state of flux. This is partly due to the elatively recent revelation that deep learning models are able to completely memorize training data and still perform appropriately on out-of-sample data, thereby contradicting long-held intuitions about generalization. The phenomenon was brought to light and discussed in a seminal paper by Zhang et al. [24]. We expand upon this work by discussing local attributes of neural network training within the context of a relatively simple and generalizable framework. We describe how various types of noise can be compensated for within the proposed framework in order to allow the global deep learning model to generalize in spite of interpolating spurious function descriptors. Empirically, we support our postulates with experiments involving overparameterized multilayer perceptrons and controlled noise in the training data. The main insights are that deep learning models are optimized for training data modularly, with different regions in the function space dedicated to fitting distinct kinds of sample information. Detrimental overfitting is largely prevented by the fact that different regions in the function space are used for prediction based on the similarity between new input data and that which has been optimized for.

@{284,
  author = {Marthinus Theunissen and Marelie Davel and Etienne Barnard},
  title = {Insights regarding overfitting on noise in deep learning},
  abstract = {The understanding of generalization in machine learning is in a state of flux. This is partly due to the elatively recent revelation that deep learning models are able to completely memorize training data and still perform appropriately on out-of-sample data, thereby contradicting long-held intuitions about generalization. The phenomenon was brought to light and discussed in a seminal paper by Zhang et al. [24]. We expand upon this work by discussing local attributes of neural network training within the context of a relatively simple and generalizable framework. We describe how various types of noise can be compensated for within the proposed framework in order to allow the global deep learning model to generalize in spite of interpolating spurious function descriptors. Empirically, we support our postulates with experiments involving overparameterized multilayer perceptrons and controlled noise in the training data. The main insights are that deep learning models are optimized for training data modularly, with different regions in the function space dedicated to fitting distinct kinds of sample information. Detrimental overfitting is largely prevented by the fact that different regions in the function space are used for prediction based on the similarity between new input data and that which has been optimized for.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {49-63},
  address = {Cape Town, South Africa},
}
Pretorius, A. P., Barnard, E., & Davel, M. H. (2019). ReLU and sigmoidal activation functions. In South African Forum for Artificial Intelligence Research (FAIR). Cape Town, South Africa: CEUR Workshop Proceedings.

The generalization capabilities of deep neural networks are not well understood, and in particular, the influence of activation functions on generalization has received little theoretical attention. Phenomena such as vanishing gradients, node saturation and network sparsity have been identified as possible factors when comparing different activation functions [1]. We investigate these factors using fully connected feedforward networks on two standard benchmark problems, and find that the most salient differences between networks with sigmoidal and ReLU activations relate to the way that class-distinctive information is propagated through a network.

@{279,
  author = {Arnold Pretorius and Etienne Barnard and Marelie Davel},
  title = {ReLU and sigmoidal activation functions},
  abstract = {The generalization capabilities of deep neural networks are not well understood, and in particular, the influence of activation functions on generalization has received little theoretical attention. Phenomena such as vanishing gradients, node saturation and network sparsity have been identified as possible factors when comparing different activation functions [1]. We investigate these factors using fully connected feedforward networks on two standard benchmark problems, and find that the most salient differences between networks with sigmoidal and ReLU activations relate to the way that class-distinctive information is propagated through a network.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {37-48},
  month = {04/12-07/12},
  publisher = {CEUR Workshop Proceedings},
  address = {Cape Town, South Africa},
}
Lotz, S., Beukes, J. P., & Davel, M. H. (2019). Input parameter ranking for neural networks in a space weather regression problem. In South African Forum for Artificial Intelligence Research (FAIR). Cape Town, South Africa: CEUR workshop proceedings.

Geomagnetic storms are multi-day events characterised by significant perturbations to the magnetic field of the Earth, driven by solar activity. Numerous efforts have been undertaken to utilise in-situ measurements of the solar wind plasma to predict perturbations to the geomagnetic field measured on the ground. Typically, solar wind measurements are used as input parameters to a regression problem tasked with predicting a perturbation index such as the 1-minute cadence symmetric-H (Sym-H) index. We re-visit this problem, with two important twists: (i) An adapted feedforward neural network topology is designed to enable the pairwise analysis of input parameter weights. This enables the ranking of input parameters in terms of importance to output accuracy, without the need to train numerous models. (ii) Geomagnetic storm phase information is incorporated as model inputs and shown to increase performance. This is motivated by the fact that different physical phenomena are at play during different phases of a geomagnetic storm.

@{283,
  author = {Stefan Lotz and Jacques Beukes and Marelie Davel},
  title = {Input parameter ranking for neural networks in a space weather regression problem},
  abstract = {Geomagnetic storms are multi-day events characterised by significant perturbations to the magnetic field of the Earth, driven by solar activity. Numerous efforts have been undertaken to utilise in-situ measurements of the solar wind plasma to predict perturbations to the geomagnetic field measured on the ground. Typically, solar wind measurements are used as input parameters to a regression problem tasked with predicting a perturbation index such as the 1-minute cadence symmetric-H (Sym-H) index. We re-visit this problem, with two important twists:
(i) An adapted feedforward neural network topology is designed to enable the pairwise analysis of input parameter weights. This enables the ranking of input parameters in terms of importance to output accuracy, without the need to train numerous models. (ii) Geomagnetic storm phase information is incorporated as model inputs and shown to increase performance. This is motivated by the fact that different physical phenomena are at play during different phases of a geomagnetic storm.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {133-144},
  publisher = {CEUR workshop proceedings},
  address = {Cape Town, South Africa},
}
Krynauw, D. D., Davel, M. H., & Lotz, S. (2019). Solar flare prediction with temporal convolutional networks (Work in progress). In South African Forum for Artificial Intelligence Research (FAIR). CEUR workshop proceedings.

Sequences are typically modelled with recurrent architectures, but growing research is finding convolutional architectures to also work well for sequence modelling [1]. We explore the performance of Temporal Convolutional Networks (TCNs) when applied to an important sequence modelling task: solar flare prediction. We take this approach, as our future goal is to apply techniques developed for probing and interpreting general convolutional neural networks (CNNs) to solar flare prediction.

@{282,
  author = {Dewald Krynauw and Marelie Davel and Stefan Lotz},
  title = {Solar flare prediction with temporal convolutional networks (Work in progress)},
  abstract = {Sequences are typically modelled with recurrent architectures, but growing research is finding convolutional architectures to also work well for sequence modelling [1]. We explore the performance of Temporal Convolutional Networks (TCNs) when applied to an important sequence modelling task: solar flare prediction. We take this approach, as our future goal is to apply techniques developed for probing and interpreting general convolutional neural networks (CNNs) to solar flare prediction.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {Work in progress},
  publisher = {CEUR workshop proceedings},
  isbn = {1613-0073},
}
Davel, M. H. (2019). Activation gap generators in neural networks. In South African Forum for Artificial Intelligence Research (FAIR). Cape Town, South Africa: CEUR workshop proceedings.

No framework exists that can explain and predict the generalisation ability of DNNs in general circumstances. In fact, this question has not been addressed for some of the least complicated of neural network architectures: fully-connected feedforward networks with ReLU activations and a limited number of hidden layers. Building on recent work [2] that demonstrates the ability of individual nodes in a hidden layer to draw class-specific activation distributions apart, we show how a simplified network architecture can be analysed in terms of these activation distributions, and more specifically, the sample distances or activation gaps each node produces. We provide a theoretical perspective on the utility of viewing nodes as activation gap generators, and define the gap conditions that are guaranteed to result in perfect classification of a set of samples. We support these conclusions with empirical results.

@{230,
  author = {Marelie Davel},
  title = {Activation gap generators in neural networks},
  abstract = {No framework exists that can explain and predict the generalisation ability of DNNs in general circumstances. In fact, this question has not been addressed for some of the least complicated of neural network architectures: fully-connected feedforward networks with ReLU activations and a limited number of hidden layers. Building on recent work [2] that demonstrates the ability of individual nodes in a hidden layer to draw class-specific activation distributions apart, we show how a simplified network architecture can be analysed in terms of these activation distributions, and more specifically, the sample distances or activation gaps each node produces. We provide a theoretical perspective on the utility of viewing nodes as activation gap generators, and define the gap conditions that are guaranteed to result in perfect classification of a set of samples. We support these conclusions with empirical results.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {64-76},
  month = {04/12-06/12/2019},
  publisher = {CEUR workshop proceedings},
  address = {Cape Town, South Africa},
}

2017

Van Niekerk, D. R., Van Heerden, C. J., Davel, M. H., Kleynhans, N., Kjartansson, O., Jansche, M., & Ha, L. (2017). Rapid development of TTS corpora for four South African languages. In Interspeech. Stockholm, Sweden. http://doi.org/10.21437/Interspeech.2017-1139

This paper describes the development of text-to-speech corpora for four South African languages. The approach followed investigated the possibility of using low-cost methods including informal recording environments and untrained volunteer speakers. This objective and the additional future goal of expanding the corpus to increase coverage of South Africa’s 11 official languages necessitated experimenting with multi-speaker and code-switched data. The process and relevant observations are detailed throughout. The latest version of the corpora are available for download under an open-source licence and will likely see further development and refinement in future.

@{278,
  author = {Daniel Van Niekerk and Charl Van Heerden and Marelie Davel and Neil Kleynhans and Oddur Kjartansson and Martin Jansche and Linne Ha},
  title = {Rapid development of TTS corpora for four South African languages},
  abstract = {This paper describes the development of text-to-speech corpora for four South African languages. The approach followed investigated the possibility of using low-cost methods including informal recording environments and untrained volunteer speakers. This objective and the additional future goal of expanding the corpus to increase coverage of South Africa’s 11 official languages necessitated experimenting with multi-speaker and code-switched data. The process and relevant observations are detailed throughout. The latest version of the corpora are available for download under an open-source licence and will likely see further development and refinement in future.},
  year = {2017},
  journal = {Interspeech},
  pages = {2178-2182},
  address = {Stockholm, Sweden},
  doi = {10.21437/Interspeech.2017-1139},
}
Van Niekerk, D. R. (2017). Evaluating acoustic modelling of lexical stress for Afrikaans speech synthesis. In Pattern Recognition Association of South Africa and Mechatronics International Conference (PRASA-RobMech). Bloemfontein, South Africa. http://doi.org/10.1109/RoboMech.2017.8261128

An explicit lexical stress feature is investigated for statistical parametric speech synthesis in Afrikaans: Firstly, objective measures are used to assess proposed annotation protocols and dictionaries compared to the baseline (implicit modelling) on the Lwazi 2 text-to-speech corpus. Secondly, the best candidates are evaluated on additional corpora. Finally, a comparative subjective evaluation is conducted to determine the perceptual impact on text-to-speech synthesis. The best candidate dictionary is associated with favourable objective results obtained on all corpora and was preferred in the subjective test. This suggests that it may form a basis for further refinement and work on improved prosodic models.

@{277,
  author = {Daniel Van Niekerk},
  title = {Evaluating acoustic modelling of lexical stress for Afrikaans speech synthesis},
  abstract = {An explicit lexical stress feature is investigated for statistical parametric speech synthesis in Afrikaans: Firstly, objective measures are used to assess proposed annotation protocols and dictionaries compared to the baseline (implicit modelling) on the Lwazi 2 text-to-speech corpus. Secondly, the best candidates are evaluated on additional corpora. Finally, a comparative subjective evaluation is conducted to determine the perceptual impact on text-to-speech synthesis. The best candidate dictionary is associated with favourable objective results obtained on all corpora and was preferred in the subjective test. This suggests that it may form a basis for further refinement and work on improved prosodic models.},
  year = {2017},
  journal = {Pattern Recognition Association of South Africa and Mechatronics International Conference (PRASA-RobMech)},
  pages = {86-91},
  address = {Bloemfontein, South Africa},
  isbn = {978-1-5386-2314-5, 978-1-5386-2313-8},
  doi = {10.1109/RoboMech.2017.8261128},
}
Van Heerden, C. J., Karakos, D., Narasimhan, K., Davel, M. H., & Schwartz, R. (2017). Constructing Sub-Word Units for Spoken Term Detection. In IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP). New Orleans, Louisiana. http://doi.org/10.1109/ICASSP.2017.7953264

Spoken term detection, especially of out-of-vocabulary (OOV) key-words, benefits from the use of sub-word systems. We experiment with different language-dependent approaches to sub-word unit generation, generating both syllable-like and morpheme-like units, and demonstrate how the performance of syllable-like units can be improved by artificially increasing the number of unique units. The effect of unit choice is empirically evaluated using the eight languages from the 2016 IARPA BABEL evaluation.

@{276,
  author = {Charl Van Heerden and Damianos Karakos and Karthik Narasimhan and Marelie Davel and Richard Schwartz},
  title = {Constructing Sub-Word Units for Spoken Term Detection},
  abstract = {Spoken term detection, especially of out-of-vocabulary (OOV) key-words, benefits from the use of sub-word systems. We experiment with different language-dependent approaches to sub-word unit generation, generating both syllable-like and morpheme-like units, and demonstrate how the performance of syllable-like units can be improved by artificially increasing the number of unique units. The effect of unit choice is empirically evaluated using the eight languages from the 2016 IARPA BABEL evaluation.},
  year = {2017},
  journal = {IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP)},
  pages = {5780-5784},
  address = {New Orleans,  Louisiana},
  isbn = {9781509041176},
  doi = {10.1109/ICASSP.2017.7953264},
}
Van der Walt, C., & Barnard, E. (2017). Variable Kernel Density Estimation in High-dimensional Feature Spaces. In AAAI Conf. on Artificial Intelligence (AAAI-17).

Estimating the joint probability density function of a dataset is a central task in many machine learning applications. In this work we address the fundamental problem of kernel bandwidth estimation for variable kernel density estimation in high-dimensional feature spaces. We derive a variable kernel bandwidth estimator by minimizing the leave-one-out entropy objective function and show that this estimator is capable of performing estimation in high-dimensional feature spaces with great success. We compare the performance of this estimator to state-of-the art maximum likelihood estimators on a number of representative high-dimensional machine learning tasks and show that the newly introduced minimum leave-one-out entropy estimator performs optimally on a number of high-dimensional datasets considered.

@{275,
  author = {Christiaan Van der Walt and Etienne Barnard},
  title = {Variable Kernel Density Estimation in High-dimensional Feature Spaces},
  abstract = {Estimating the joint probability density function of a dataset is a central task in many machine learning applications. In this work we address the fundamental problem of kernel bandwidth estimation for variable kernel density estimation in high-dimensional feature spaces. We derive a variable kernel bandwidth estimator by minimizing the leave-one-out entropy objective function and show that this estimator is capable of performing estimation in high-dimensional feature spaces with great success. We compare the performance of this estimator to state-of-the art maximum likelihood estimators on a number of representative high-dimensional machine learning tasks and show that the newly introduced minimum leave-one-out entropy estimator performs optimally on a number of high-dimensional datasets considered.},
  year = {2017},
  journal = {AAAI Conf. on Artificial Intelligence (AAAI-17)},
  pages = {2674-2680},
  month = {04/02-09/04},
}
Giwa, O., & Davel, M. H. (2017). The Effect of Language Identification Accuracy on Speech Recognition Accuracy of Proper Names. In Pattern Recognition Association of South Africa and Mechatronics International Conference (PRASA-RobMech). Bloemfontein, South Africa. http://doi.org/10.1109/RoboMech.2017.8261145

Utilizing the known language of origin of a name can be useful when predicting the pronunciation of the name. When this language is not known, automatic language identification (LID) can be used to influence which language-specific grapheme-to-phoneme (G2P) predictor is triggered to produce a pronunciation for the name. We investigate the implications when both the LID system and the G2P system generate errors: what influence does this have on a resulting speech recognition system? We experiment with different approaches to LID-based dictionary creation and report on results in four South African languages: Afrikaans, English, Sesotho and isiZulu.

@{274,
  author = {Oluwapelumi Giwa and Marelie Davel},
  title = {The Effect of Language Identification Accuracy on Speech Recognition Accuracy of Proper Names},
  abstract = {Utilizing the known language of origin of a name can be useful when predicting the pronunciation of the name. When this language is not known, automatic language identification (LID) can be used to influence which language-specific grapheme-to-phoneme (G2P) predictor is triggered to produce a pronunciation for the name. We investigate the implications when both the LID system and the G2P system generate errors: what influence does this have on a resulting speech recognition system? We experiment with different approaches to LID-based dictionary creation and report on results in four South African languages: Afrikaans, English, Sesotho and isiZulu.},
  year = {2017},
  journal = {Pattern Recognition Association of South Africa and Mechatronics International Conference (PRASA-RobMech)},
  pages = {187-192},
  address = {Bloemfontein, South Africa},
  isbn = {978-1-5386-2314-5, 978-1-5386-2313-8},
  doi = {10.1109/RoboMech.2017.8261145},
}
  • DSI
  • Covid-19